Google Git
Sign in
code / google-api-go-client / 9e2045da407b8bc1df9bc5c14d4d1a7e7e182e05 / . / dataflow / v1b3 / dataflow-api.json
blob: 1d0294f4628bd8e227959e775ee6889bb8310c68 [file] [log] [blame]
{
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
},
"https://www.googleapis.com/auth/userinfo.email": {
"description": "View your email address"
},
"https://www.googleapis.com/auth/compute.readonly": {
"description": "View your Google Compute Engine resources"
},
"https://www.googleapis.com/auth/compute": {
"description": "View and manage your Google Compute Engine resources"
}
}
}
},
"kind": "discovery#restDescription",
"description": "Manages Google Cloud Dataflow projects on Google Cloud Platform.",
"servicePath": "",
"rootUrl": "https://dataflow.googleapis.com/",
"basePath": "",
"ownerDomain": "google.com",
"name": "dataflow",
"batchPath": "batch",
"id": "dataflow:v1b3",
"documentationLink": "https://cloud.google.com/dataflow",
"revision": "20171003",
"title": "Google Dataflow API",
"discoveryVersion": "v1",
"ownerName": "Google",
"resources": {
"projects": {
"methods": {
"workerMessages": {
"flatPath": "v1b3/projects/{projectId}/WorkerMessages",
"id": "dataflow.projects.workerMessages",
"path": "v1b3/projects/{projectId}/WorkerMessages",
"request": {
"$ref": "SendWorkerMessagesRequest"
},
"description": "Send a worker_message to the service.",
"response": {
"$ref": "SendWorkerMessagesResponse"
},
"parameterOrder": [
"projectId"
],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The project to send the WorkerMessages to."
}
}
}
},
"resources": {
"locations": {
"methods": {
"workerMessages": {
"response": {
"$ref": "SendWorkerMessagesResponse"
},
"parameterOrder": [
"projectId",
"location"
],
"httpMethod": "POST",
"parameters": {
"projectId": {
"location": "path",
"description": "The project to send the WorkerMessages to.",
"type": "string",
"required": true
},
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location which contains the job"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/WorkerMessages",
"id": "dataflow.projects.locations.workerMessages",
"path": "v1b3/projects/{projectId}/locations/{location}/WorkerMessages",
"description": "Send a worker_message to the service.",
"request": {
"$ref": "SendWorkerMessagesRequest"
}
}
},
"resources": {
"templates": {
"methods": {
"get": {
"description": "Get the template associated with a template.",
"httpMethod": "GET",
"response": {
"$ref": "GetTemplateResponse"
},
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"location": {
"location": "path",
"description": "The location to which to direct the request.",
"type": "string",
"required": true
},
"view": {
"location": "query",
"enum": [
"METADATA_ONLY"
],
"description": "The view to retrieve. Defaults to METADATA_ONLY.",
"type": "string"
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "Required. The ID of the Cloud Platform project that the job belongs to."
},
"gcsPath": {
"location": "query",
"description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"type": "string"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/templates:get",
"path": "v1b3/projects/{projectId}/locations/{location}/templates:get",
"id": "dataflow.projects.locations.templates.get"
},
"create": {
"flatPath": "v1b3/projects/{projectId}/locations/{location}/templates",
"id": "dataflow.projects.locations.templates.create",
"path": "v1b3/projects/{projectId}/locations/{location}/templates",
"description": "Creates a Cloud Dataflow job from a template.",
"request": {
"$ref": "CreateJobFromTemplateRequest"
},
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId",
"location"
],
"httpMethod": "POST",
"parameters": {
"location": {
"location": "path",
"description": "The location to which to direct the request.",
"type": "string",
"required": true
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "Required. The ID of the Cloud Platform project that the job belongs to."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"launch": {
"description": "Launch a template.",
"request": {
"$ref": "LaunchTemplateParameters"
},
"httpMethod": "POST",
"parameterOrder": [
"projectId",
"location"
],
"response": {
"$ref": "LaunchTemplateResponse"
},
"parameters": {
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location to which to direct the request."
},
"validateOnly": {
"location": "query",
"description": "If true, the request is validated but not actually executed.\nDefaults to false.",
"type": "boolean"
},
"projectId": {
"location": "path",
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"type": "string",
"required": true
},
"gcsPath": {
"type": "string",
"location": "query",
"description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
"path": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
"id": "dataflow.projects.locations.templates.launch"
}
}
},
"jobs": {
"methods": {
"list": {
"httpMethod": "GET",
"response": {
"$ref": "ListJobsResponse"
},
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The project which owns the jobs."
},
"filter": {
"location": "query",
"enum": [
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"description": "The kind of filter to use.",
"type": "string"
},
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location that contains this job."
},
"pageToken": {
"location": "query",
"description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"type": "string"
},
"pageSize": {
"type": "integer",
"location": "query",
"format": "int32",
"description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit."
},
"view": {
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
"type": "string"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs",
"id": "dataflow.projects.locations.jobs.list",
"description": "List the jobs of a project in a given region."
},
"get": {
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"httpMethod": "GET",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"view": {
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "The level of information requested in response.",
"type": "string"
},
"jobId": {
"type": "string",
"required": true,
"location": "path",
"description": "The job ID."
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The ID of the Cloud Platform project that the job belongs to."
},
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location that contains this job."
}
},
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"id": "dataflow.projects.locations.jobs.get",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"description": "Gets the state of the specified Cloud Dataflow job."
},
"update": {
"httpMethod": "PUT",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location that contains this job."
},
"jobId": {
"location": "path",
"description": "The job ID.",
"type": "string",
"required": true
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The ID of the Cloud Platform project that the job belongs to."
}
},
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"id": "dataflow.projects.locations.jobs.update",
"request": {
"$ref": "Job"
},
"description": "Updates the state of an existing Cloud Dataflow job."
},
"create": {
"description": "Creates a Cloud Dataflow job.",
"request": {
"$ref": "Job"
},
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId",
"location"
],
"httpMethod": "POST",
"parameters": {
"view": {
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "The level of information requested in response.",
"type": "string"
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The ID of the Cloud Platform project that the job belongs to."
},
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location that contains this job."
},
"replaceJobId": {
"type": "string",
"location": "query",
"description": "Deprecated. This field is now in the Job message."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs",
"id": "dataflow.projects.locations.jobs.create",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs"
},
"getMetrics": {
"httpMethod": "GET",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"response": {
"$ref": "JobMetrics"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"jobId": {
"location": "path",
"description": "The job to get messages for.",
"type": "string",
"required": true
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "A project id."
},
"location": {
"location": "path",
"description": "The location which contains the job specified by job_id.",
"type": "string",
"required": true
},
"startTime": {
"location": "query",
"format": "google-datetime",
"description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
"type": "string"
}
},
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
"id": "dataflow.projects.locations.jobs.getMetrics",
"description": "Request the job status."
}
},
"resources": {
"workItems": {
"methods": {
"lease": {
"request": {
"$ref": "LeaseWorkItemRequest"
},
"description": "Leases a dataflow WorkItem to run.",
"httpMethod": "POST",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"response": {
"$ref": "LeaseWorkItemResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"jobId": {
"type": "string",
"required": true,
"location": "path",
"description": "Identifies the workflow job this worker belongs to."
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "Identifies the project this worker belongs to."
},
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location which contains the WorkItem's job."
}
},
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
"id": "dataflow.projects.locations.jobs.workItems.lease"
},
"reportStatus": {
"httpMethod": "POST",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"response": {
"$ref": "ReportWorkItemStatusResponse"
},
"parameters": {
"location": {
"location": "path",
"description": "The location which contains the WorkItem's job.",
"type": "string",
"required": true
},
"jobId": {
"location": "path",
"description": "The job which the WorkItem is part of.",
"type": "string",
"required": true
},
"projectId": {
"location": "path",
"description": "The project which owns the WorkItem's job.",
"type": "string",
"required": true
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
"id": "dataflow.projects.locations.jobs.workItems.reportStatus",
"description": "Reports the status of dataflow WorkItems leased by a worker.",
"request": {
"$ref": "ReportWorkItemStatusRequest"
}
}
}
},
"debug": {
"methods": {
"sendCapture": {
"description": "Send encoded debug capture data for component.",
"request": {
"$ref": "SendDebugCaptureRequest"
},
"httpMethod": "POST",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"response": {
"$ref": "SendDebugCaptureResponse"
},
"parameters": {
"location": {
"location": "path",
"description": "The location which contains the job specified by job_id.",
"type": "string",
"required": true
},
"jobId": {
"location": "path",
"description": "The job id.",
"type": "string",
"required": true
},
"projectId": {
"location": "path",
"description": "The project id.",
"type": "string",
"required": true
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/sendCapture",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/sendCapture",
"id": "dataflow.projects.locations.jobs.debug.sendCapture"
},
"getConfig": {
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getConfig",
"id": "dataflow.projects.locations.jobs.debug.getConfig",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getConfig",
"description": "Get encoded debug configuration for component. Not cacheable.",
"request": {
"$ref": "GetDebugConfigRequest"
},
"response": {
"$ref": "GetDebugConfigResponse"
},
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"httpMethod": "POST",
"parameters": {
"jobId": {
"location": "path",
"description": "The job id.",
"type": "string",
"required": true
},
"projectId": {
"location": "path",
"description": "The project id.",
"type": "string",
"required": true
},
"location": {
"type": "string",
"required": true,
"location": "path",
"description": "The location which contains the job specified by job_id."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
},
"messages": {
"methods": {
"list": {
"response": {
"$ref": "ListJobMessagesResponse"
},
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"httpMethod": "GET",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"minimumImportance": {
"type": "string",
"location": "query",
"enum": [
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"description": "Filter to only get messages with importance \u003e= level"
},
"jobId": {
"location": "path",
"description": "The job to get messages about.",
"type": "string",
"required": true
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "A project id."
},
"endTime": {
"location": "query",
"format": "google-datetime",
"description": "Return only messages with timestamps \u003c end_time. The default is now\n(i.e. return up to the latest messages available).",
"type": "string"
},
"location": {
"location": "path",
"description": "The location which contains the job specified by job_id.",
"type": "string",
"required": true
},
"pageToken": {
"location": "query",
"description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
"type": "string"
},
"startTime": {
"location": "query",
"format": "google-datetime",
"description": "If specified, return only messages with timestamps \u003e= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
"type": "string"
},
"pageSize": {
"type": "integer",
"location": "query",
"format": "int32",
"description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results."
}
},
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
"id": "dataflow.projects.locations.jobs.messages.list",
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
"description": "Request the job status."
}
}
}
}
}
}
},
"templates": {
"methods": {
"get": {
"description": "Get the template associated with a template.",
"response": {
"$ref": "GetTemplateResponse"
},
"parameterOrder": [
"projectId"
],
"httpMethod": "GET",
"parameters": {
"view": {
"type": "string",
"location": "query",
"enum": [
"METADATA_ONLY"
],
"description": "The view to retrieve. Defaults to METADATA_ONLY."
},
"projectId": {
"location": "path",
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"type": "string",
"required": true
},
"gcsPath": {
"type": "string",
"location": "query",
"description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`."
},
"location": {
"type": "string",
"location": "query",
"description": "The location to which to direct the request."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/templates:get",
"id": "dataflow.projects.templates.get",
"path": "v1b3/projects/{projectId}/templates:get"
},
"create": {
"flatPath": "v1b3/projects/{projectId}/templates",
"id": "dataflow.projects.templates.create",
"path": "v1b3/projects/{projectId}/templates",
"description": "Creates a Cloud Dataflow job from a template.",
"request": {
"$ref": "CreateJobFromTemplateRequest"
},
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId"
],
"httpMethod": "POST",
"parameters": {
"projectId": {
"location": "path",
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"type": "string",
"required": true
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"launch": {
"flatPath": "v1b3/projects/{projectId}/templates:launch",
"path": "v1b3/projects/{projectId}/templates:launch",
"id": "dataflow.projects.templates.launch",
"description": "Launch a template.",
"request": {
"$ref": "LaunchTemplateParameters"
},
"httpMethod": "POST",
"parameterOrder": [
"projectId"
],
"response": {
"$ref": "LaunchTemplateResponse"
},
"parameters": {
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "Required. The ID of the Cloud Platform project that the job belongs to."
},
"gcsPath": {
"type": "string",
"location": "query",
"description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'."
},
"location": {
"type": "string",
"location": "query",
"description": "The location to which to direct the request."
},
"validateOnly": {
"type": "boolean",
"location": "query",
"description": "If true, the request is validated but not actually executed.\nDefaults to false."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
},
"jobs": {
"methods": {
"getMetrics": {
"description": "Request the job status.",
"response": {
"$ref": "JobMetrics"
},
"parameterOrder": [
"projectId",
"jobId"
],
"httpMethod": "GET",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"jobId": {
"location": "path",
"description": "The job to get messages for.",
"type": "string",
"required": true
},
"projectId": {
"location": "path",
"description": "A project id.",
"type": "string",
"required": true
},
"location": {
"location": "query",
"description": "The location which contains the job specified by job_id.",
"type": "string"
},
"startTime": {
"type": "string",
"location": "query",
"format": "google-datetime",
"description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job."
}
},
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
"id": "dataflow.projects.jobs.getMetrics",
"path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics"
},
"get": {
"httpMethod": "GET",
"parameterOrder": [
"projectId",
"jobId"
],
"response": {
"$ref": "Job"
},
"parameters": {
"location": {
"type": "string",
"location": "query",
"description": "The location that contains this job."
},
"view": {
"type": "string",
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "The level of information requested in response."
},
"jobId": {
"type": "string",
"required": true,
"location": "path",
"description": "The job ID."
},
"projectId": {
"location": "path",
"description": "The ID of the Cloud Platform project that the job belongs to.",
"type": "string",
"required": true
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}",
"path": "v1b3/projects/{projectId}/jobs/{jobId}",
"id": "dataflow.projects.jobs.get",
"description": "Gets the state of the specified Cloud Dataflow job."
},
"update": {
"httpMethod": "PUT",
"parameterOrder": [
"projectId",
"jobId"
],
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"location": {
"location": "query",
"description": "The location that contains this job.",
"type": "string"
},
"jobId": {
"type": "string",
"required": true,
"location": "path",
"description": "The job ID."
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The ID of the Cloud Platform project that the job belongs to."
}
},
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}",
"path": "v1b3/projects/{projectId}/jobs/{jobId}",
"id": "dataflow.projects.jobs.update",
"request": {
"$ref": "Job"
},
"description": "Updates the state of an existing Cloud Dataflow job."
},
"aggregated": {
"response": {
"$ref": "ListJobsResponse"
},
"parameterOrder": [
"projectId"
],
"httpMethod": "GET",
"parameters": {
"view": {
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
"type": "string"
},
"projectId": {
"location": "path",
"description": "The project which owns the jobs.",
"type": "string",
"required": true
},
"filter": {
"type": "string",
"location": "query",
"enum": [
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"description": "The kind of filter to use."
},
"location": {
"type": "string",
"location": "query",
"description": "The location that contains this job."
},
"pageToken": {
"location": "query",
"description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"type": "string"
},
"pageSize": {
"location": "query",
"format": "int32",
"description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
"type": "integer"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/jobs:aggregated",
"id": "dataflow.projects.jobs.aggregated",
"path": "v1b3/projects/{projectId}/jobs:aggregated",
"description": "List the jobs of a project across all regions."
},
"list": {
"description": "List the jobs of a project in a given region.",
"httpMethod": "GET",
"response": {
"$ref": "ListJobsResponse"
},
"parameterOrder": [
"projectId"
],
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The project which owns the jobs."
},
"filter": {
"type": "string",
"location": "query",
"enum": [
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"description": "The kind of filter to use."
},
"location": {
"type": "string",
"location": "query",
"description": "The location that contains this job."
},
"pageToken": {
"location": "query",
"description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"type": "string"
},
"pageSize": {
"location": "query",
"format": "int32",
"description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
"type": "integer"
},
"view": {
"type": "string",
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`."
}
},
"flatPath": "v1b3/projects/{projectId}/jobs",
"path": "v1b3/projects/{projectId}/jobs",
"id": "dataflow.projects.jobs.list"
},
"create": {
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId"
],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"location": {
"type": "string",
"location": "query",
"description": "The location that contains this job."
},
"replaceJobId": {
"location": "query",
"description": "Deprecated. This field is now in the Job message.",
"type": "string"
},
"view": {
"type": "string",
"location": "query",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"description": "The level of information requested in response."
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The ID of the Cloud Platform project that the job belongs to."
}
},
"flatPath": "v1b3/projects/{projectId}/jobs",
"id": "dataflow.projects.jobs.create",
"path": "v1b3/projects/{projectId}/jobs",
"request": {
"$ref": "Job"
},
"description": "Creates a Cloud Dataflow job."
}
},
"resources": {
"workItems": {
"methods": {
"lease": {
"response": {
"$ref": "LeaseWorkItemResponse"
},
"parameterOrder": [
"projectId",
"jobId"
],
"httpMethod": "POST",
"parameters": {
"jobId": {
"location": "path",
"description": "Identifies the workflow job this worker belongs to.",
"type": "string",
"required": true
},
"projectId": {
"location": "path",
"description": "Identifies the project this worker belongs to.",
"type": "string",
"required": true
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
"id": "dataflow.projects.jobs.workItems.lease",
"path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
"description": "Leases a dataflow WorkItem to run.",
"request": {
"$ref": "LeaseWorkItemRequest"
}
},
"reportStatus": {
"request": {
"$ref": "ReportWorkItemStatusRequest"
},
"description": "Reports the status of dataflow WorkItems leased by a worker.",
"httpMethod": "POST",
"parameterOrder": [
"projectId",
"jobId"
],
"response": {
"$ref": "ReportWorkItemStatusResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"jobId": {
"location": "path",
"description": "The job which the WorkItem is part of.",
"type": "string",
"required": true
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The project which owns the WorkItem's job."
}
},
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus",
"path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus",
"id": "dataflow.projects.jobs.workItems.reportStatus"
}
}
},
"debug": {
"methods": {
"sendCapture": {
"response": {
"$ref": "SendDebugCaptureResponse"
},
"parameterOrder": [
"projectId",
"jobId"
],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"parameters": {
"jobId": {
"location": "path",
"description": "The job id.",
"type": "string",
"required": true
},
"projectId": {
"location": "path",
"description": "The project id.",
"type": "string",
"required": true
}
},
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
"id": "dataflow.projects.jobs.debug.sendCapture",
"path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
"request": {
"$ref": "SendDebugCaptureRequest"
},
"description": "Send encoded debug capture data for component."
},
"getConfig": {
"httpMethod": "POST",
"parameterOrder": [
"projectId",
"jobId"
],
"response": {
"$ref": "GetDebugConfigResponse"
},
"parameters": {
"jobId": {
"location": "path",
"description": "The job id.",
"type": "string",
"required": true
},
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "The project id."
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
],
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
"path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
"id": "dataflow.projects.jobs.debug.getConfig",
"description": "Get encoded debug configuration for component. Not cacheable.",
"request": {
"$ref": "GetDebugConfigRequest"
}
}
}
},
"messages": {
"methods": {
"list": {
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
"path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
"id": "dataflow.projects.jobs.messages.list",
"description": "Request the job status.",
"httpMethod": "GET",
"parameterOrder": [
"projectId",
"jobId"
],
"response": {
"$ref": "ListJobMessagesResponse"
},
"parameters": {
"projectId": {
"type": "string",
"required": true,
"location": "path",
"description": "A project id."
},
"jobId": {
"location": "path",
"description": "The job to get messages about.",
"type": "string",
"required": true
},
"location": {
"type": "string",
"location": "query",
"description": "The location which contains the job specified by job_id."
},
"endTime": {
"location": "query",
"format": "google-datetime",
"description": "Return only messages with timestamps \u003c end_time. The default is now\n(i.e. return up to the latest messages available).",
"type": "string"
},
"startTime": {
"type": "string",
"location": "query",
"format": "google-datetime",
"description": "If specified, return only messages with timestamps \u003e= start_time.\nThe default is the job creation time (i.e. beginning of messages)."
},
"pageToken": {
"location": "query",
"description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
"type": "string"
},
"pageSize": {
"type": "integer",
"location": "query",
"format": "int32",
"description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results."
},
"minimumImportance": {
"location": "query",
"enum": [
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"description": "Filter to only get messages with importance \u003e= level",
"type": "string"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
}
}
}
}
}
},
"parameters": {
"uploadType": {
"location": "query",
"description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"type": "string"
},
"fields": {
"location": "query",
"description": "Selector specifying which fields to include in a partial response.",
"type": "string"
},
"$.xgafv": {
"location": "query",
"enum": [
"1",
"2"
],
"description": "V1 error format.",
"type": "string",
"enumDescriptions": [
"v1 error format",
"v2 error format"
]
},
"callback": {
"location": "query",
"description": "JSONP",
"type": "string"
},
"alt": {
"type": "string",
"enumDescriptions": [
"Responses with Content-Type of application/json",
"Media download with context-dependent Content-Type",
"Responses with Content-Type of application/x-protobuf"
],
"location": "query",
"description": "Data format for response.",
"default": "json",
"enum": [
"json",
"media",
"proto"
]
},
"access_token": {
"type": "string",
"location": "query",
"description": "OAuth access token."
},
"key": {
"type": "string",
"location": "query",
"description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token."
},
"quotaUser": {
"location": "query",
"description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
"type": "string"
},
"pp": {
"default": "true",
"type": "boolean",
"location": "query",
"description": "Pretty-print response."
},
"bearer_token": {
"location": "query",
"description": "OAuth bearer token.",
"type": "string"
},
"oauth_token": {
"location": "query",
"description": "OAuth 2.0 token for the current user.",
"type": "string"
},
"upload_protocol": {
"type": "string",
"location": "query",
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\")."
},
"prettyPrint": {
"location": "query",
"description": "Returns response with indentations and line breaks.",
"default": "true",
"type": "boolean"
}
},
"schemas": {
"ParDoInstruction": {
"description": "An instruction that does a ParDo operation.\nTakes one main input and zero or more side inputs, and produces\nzero or more outputs.\nRuns user code.",
"type": "object",
"properties": {
"sideInputs": {
"items": {
"$ref": "SideInputInfo"
},
"type": "array",
"description": "Zero or more side inputs."
},
"multiOutputInfos": {
"items": {
"$ref": "MultiOutputInfo"
},
"type": "array",
"description": "Information about each of the outputs, if user_fn is a MultiDoFn."
},
"userFn": {
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "The user function to invoke.",
"type": "object"
},
"input": {
"$ref": "InstructionInput",
"description": "The input."
},
"numOutputs": {
"type": "integer",
"format": "int32",
"description": "The number of outputs."
}
},
"id": "ParDoInstruction"
},
"WorkerShutdownNotice": {
"description": "Shutdown notification from workers. This is to be sent by the shutdown\nscript of the worker VM so that the backend knows that the VM is being\nshut down.",
"type": "object",
"properties": {
"reason": {
"type": "string",
"description": "The reason for the worker shutdown.\nCurrent possible values are:\n \"UNKNOWN\": shutdown reason is unknown.\n \"PREEMPTION\": shutdown reason is preemption.\nOther possible reasons may be added in the future."
}
},
"id": "WorkerShutdownNotice"
},
"CounterStructuredName": {
"description": "Identifies a counter within a per-job namespace. Counters whose structured\nnames are the same get merged into a single value for the job.",
"type": "object",
"properties": {
"originalShuffleStepName": {
"description": "The GroupByKey step name from the original graph.",
"type": "string"
},
"originalStepName": {
"type": "string",
"description": "System generated name of the original step in the user's graph, before\noptimization."
},
"workerId": {
"description": "ID of a particular worker.",
"type": "string"
},
"originNamespace": {
"type": "string",
"description": "A string containing a more specific namespace of the counter's origin."
},
"sideInput": {
"$ref": "SideInputId",
"description": "ID of a side input being read from/written to. Side inputs are identified\nby a pair of (reader, input_index). The reader is usually equal to the\noriginal name, but it may be different, if a ParDo emits it's Iterator /\nMap side input object."
},
"executionStepName": {
"description": "Name of the stage. An execution step contains multiple component steps.",
"type": "string"
},
"name": {
"type": "string",
"description": "Counter name. Not necessarily globally-unique, but unique within the\ncontext of the other fields.\nRequired."
},
"origin": {
"type": "string",
"enumDescriptions": [
"Counter was created by the Dataflow system.",
"Counter was created by the user."
],
"enum": [
"SYSTEM",
"USER"
],
"description": "One of the standard Origins defined above."
},
"componentStepName": {
"type": "string",
"description": "Name of the optimized step being executed by the workers."
},
"portion": {
"type": "string",
"enumDescriptions": [
"Counter portion has not been set.",
"Counter reports a key.",
"Counter reports a value."
],
"enum": [
"ALL",
"KEY",
"VALUE"
],
"description": "Portion of this counter, either key or value."
}
},
"id": "CounterStructuredName"
},
"MetricUpdate": {
"type": "object",
"properties": {
"set": {
"description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.",
"type": "any"
},
"cumulative": {
"description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.",
"type": "boolean"
},
"internal": {
"type": "any",
"description": "Worker-computed aggregate value for internal use by the Dataflow\nservice."
},
"kind": {
"type": "string",
"description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value."
},
"scalar": {
"description": "Worker-computed aggregate value for aggregation kinds \"Sum\", \"Max\", \"Min\",\n\"And\", and \"Or\". The possible value types are Long, Double, and Boolean.",
"type": "any"
},
"meanCount": {
"description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the count of the aggregated values and is used in combination\nwith mean_sum above to obtain the actual mean aggregate value.\nThe only possible value type is Long.",
"type": "any"
},
"meanSum": {
"description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the sum of the aggregated values and is used in combination\nwith mean_count below to obtain the actual mean aggregate value.\nThe only possible value types are Long and Double.",
"type": "any"
},
"updateTime": {
"type": "string",
"format": "google-datetime",
"description": "Timestamp associated with the metric value. Optional when workers are\nreporting work progress; it will be filled in responses from the\nmetrics API."
},
"name": {
"$ref": "MetricStructuredName",
"description": "Name of the metric."
},
"distribution": {
"description": "A struct value describing properties of a distribution of numeric values.",
"type": "any"
}
},
"id": "MetricUpdate",
"description": "Describes the state of a metric."
},
"ApproximateProgress": {
"description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
"type": "object",
"properties": {
"percentComplete": {
"type": "number",
"format": "float",
"description": "Obsolete."
},
"remainingTime": {
"type": "string",
"format": "google-duration",
"description": "Obsolete."
},
"position": {
"$ref": "Position",
"description": "Obsolete."
}
},
"id": "ApproximateProgress"
},
"WorkerMessageResponse": {
"type": "object",
"properties": {
"workerShutdownNoticeResponse": {
"$ref": "WorkerShutdownNoticeResponse",
"description": "Service's response to shutdown notice (currently empty)."
},
"workerMetricsResponse": {
"$ref": "ResourceUtilizationReportResponse",
"description": "Service's response to reporting worker metrics (currently empty)."
},
"workerHealthReportResponse": {
"$ref": "WorkerHealthReportResponse",
"description": "The service's response to a worker's health report."
}
},
"id": "WorkerMessageResponse",
"description": "A worker_message response allows the server to pass information to the\nsender."
},
"TemplateMetadata": {
"description": "Metadata describing a template.",
"type": "object",
"properties": {
"parameters": {
"description": "The parameters for the template.",
"items": {
"$ref": "ParameterMetadata"
},
"type": "array"
},
"name": {
"description": "Required. The name of the template.",
"type": "string"
},
"description": {
"description": "Optional. A description of the template.",
"type": "string"
}
},
"id": "TemplateMetadata"
},
"WorkerMessage": {
"description": "WorkerMessage provides information to the backend about a worker.",
"type": "object",
"properties": {
"time": {
"type": "string",
"format": "google-datetime",
"description": "The timestamp of the worker_message."
},
"workerShutdownNotice": {
"$ref": "WorkerShutdownNotice",
"description": "Shutdown notice by workers."
},
"workerHealthReport": {
"$ref": "WorkerHealthReport",
"description": "The health of a worker."
},
"workerMessageCode": {
"$ref": "WorkerMessageCode",
"description": "A worker message code."
},
"workerMetrics": {
"$ref": "ResourceUtilizationReport",
"description": "Resource metrics reported by workers."
},
"labels": {
"additionalProperties": {
"type": "string"
},
"description": "Labels are used to group WorkerMessages.\nFor example, a worker_message about a particular container\nmight have the labels:\n{ \"JOB_ID\": \"2015-04-22\",\n \"WORKER_ID\": \"wordcount-vm-2015…\"\n \"CONTAINER_TYPE\": \"worker\",\n \"CONTAINER_ID\": \"ac1234def\"}\nLabel tags typically correspond to Label enum values. However, for ease\nof development other strings can be used as tags. LABEL_UNSPECIFIED should\nnot be used here.",
"type": "object"
}
},
"id": "WorkerMessage"
},
"WorkerShutdownNoticeResponse": {
"type": "object",
"properties": {},
"id": "WorkerShutdownNoticeResponse",
"description": "Service-side response to WorkerMessage issuing shutdown notice."
},
"JobMetrics": {
"description": "JobMetrics contains a collection of metrics descibing the detailed progress\nof a Dataflow job. Metrics correspond to user-defined and system-defined\nmetrics in the job.\n\nThis resource captures only the most recent values of each metric;\ntime-series data can be queried for them (under the same metric names)\nfrom Cloud Monitoring.",
"type": "object",
"properties": {
"metrics": {
"description": "All metrics for this job.",
"items": {
"$ref": "MetricUpdate"
},
"type": "array"
},
"metricTime": {
"format": "google-datetime",
"description": "Timestamp as of which metric values are current.",
"type": "string"
}
},
"id": "JobMetrics"
},
"FloatingPointList": {
"type": "object",
"properties": {
"elements": {
"description": "Elements of the list.",
"items": {
"type": "number",
"format": "double"
},
"type": "array"
}
},
"id": "FloatingPointList",
"description": "A metric value representing a list of floating point numbers."
},
"CounterUpdate": {
"description": "An update to a Counter sent from a worker.",
"type": "object",
"properties": {
"integer": {
"$ref": "SplitInt64",
"description": "Integer value for Sum, Max, Min."
},
"structuredNameAndMetadata": {
"$ref": "CounterStructuredNameAndMetadata",
"description": "Counter structured name and metadata."
},
"integerList": {
"$ref": "IntegerList",
"description": "List of integers, for Set."
},
"floatingPoint": {
"format": "double",
"description": "Floating point value for Sum, Max, Min.",
"type": "number"
},
"integerMean": {
"$ref": "IntegerMean",
"description": "Integer mean aggregation value for Mean."
},
"internal": {
"type": "any",
"description": "Value for internally-defined counters used by the Dataflow service."
},
"cumulative": {
"type": "boolean",
"description": "True if this counter is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this counter is reported\nas a delta."
},
"floatingPointMean": {
"$ref": "FloatingPointMean",
"description": "Floating point mean aggregation value for Mean."
},
"boolean": {
"description": "Boolean value for And, Or.",
"type": "boolean"
},
"nameAndKind": {
"$ref": "NameAndKind",
"description": "Counter name and aggregation type."
},
"distribution": {
"$ref": "DistributionUpdate",
"description": "Distribution data"
},
"stringList": {
"$ref": "StringList",
"description": "List of strings, for Set."
},
"shortId": {
"type": "string",
"format": "int64",
"description": "The service-generated short identifier for this counter.\nThe short_id -\u003e (name, metadata) mapping is constant for the lifetime of\na job."
},
"floatingPointList": {
"$ref": "FloatingPointList",
"description": "List of floating point numbers, for Set."
}
},
"id": "CounterUpdate"
},
"SourceMetadata": {
"type": "object",
"properties": {
"estimatedSizeBytes": {
"format": "int64",
"description": "An estimate of the total size (in bytes) of the data that would be\nread from this source. This estimate is in terms of external storage\nsize, before any decompression or other processing done by the reader.",
"type": "string"
},
"infinite": {
"description": "Specifies that the size of this source is known to be infinite\n(this is a streaming source).",
"type": "boolean"
},
"producesSortedKeys": {
"description": "Whether this source is known to produce key/value pairs with\nthe (encoded) keys in lexicographically sorted order.",
"type": "boolean"
}
},
"id": "SourceMetadata",
"description": "Metadata about a Source useful for automatically optimizing\nand tuning the pipeline, etc."
},
"DistributionUpdate": {
"type": "object",
"properties": {
"count": {
"$ref": "SplitInt64",
"description": "The count of the number of elements present in the distribution."
},
"min": {
"$ref": "SplitInt64",
"description": "The minimum value present in the distribution."
},
"sumOfSquares": {
"type": "number",
"format": "double",
"description": "Use a double since the sum of squares is likely to overflow int64."
},
"sum": {
"$ref": "SplitInt64",
"description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
},
"max": {
"$ref": "SplitInt64",
"description": "The maximum value present in the distribution."
},
"histogram": {
"$ref": "Histogram",
"description": "(Optional) Histogram of value counts for the distribution."
}
},
"id": "DistributionUpdate",
"description": "A metric value representing a distribution."
},
"WorkerHealthReportResponse": {
"type": "object",
"properties": {
"reportInterval": {
"type": "string",
"format": "google-duration",
"description": "A positive value indicates the worker should change its reporting interval\nto the specified value.\n\nThe default value of zero means no change in report rate is requested by\nthe server."
}
},
"id": "WorkerHealthReportResponse",
"description": "WorkerHealthReportResponse contains information returned to the worker\nin response to a health ping."
},
"SourceFork": {
"description": "DEPRECATED in favor of DynamicSourceSplit.",
"type": "object",
"properties": {
"residual": {
"$ref": "SourceSplitShard",
"description": "DEPRECATED"
},
"residualSource": {
"$ref": "DerivedSource",
"description": "DEPRECATED"
},
"primary": {
"$ref": "SourceSplitShard",
"description": "DEPRECATED"
},
"primarySource": {
"$ref": "DerivedSource",
"description": "DEPRECATED"
}
},
"id": "SourceFork"
},
"WorkItemStatus": {
"description": "Conveys a worker's progress through the work described by a WorkItem.",
"type": "object",
"properties": {
"workItemId": {
"description": "Identifies the WorkItem.",
"type": "string"
},
"metricUpdates": {
"items": {
"$ref": "MetricUpdate"
},
"type": "array",
"description": "DEPRECATED in favor of counter_updates."
},
"errors": {
"items": {
"$ref": "Status"
},
"type": "array",
"description": "Specifies errors which occurred during processing. If errors are\nprovided, and completed = true, then the WorkItem is considered\nto have failed."
},
"dynamicSourceSplit": {
"$ref": "DynamicSourceSplit",
"description": "See documentation of stop_position."
},
"sourceOperationResponse": {
"$ref": "SourceOperationResponse",
"description": "If the work item represented a SourceOperationRequest, and the work\nis completed, contains the result of the operation."
},
"progress": {
"$ref": "ApproximateProgress",
"description": "DEPRECATED in favor of reported_progress."
},
"requestedLeaseDuration": {
"format": "google-duration",
"description": "Amount of time the worker requests for its lease.",
"type": "string"
},
"reportIndex": {
"format": "int64",
"description": "The report index. When a WorkItem is leased, the lease will\ncontain an initial report index. When a WorkItem's status is\nreported to the system, the report should be sent with\nthat report index, and the response will contain the index the\nworker should use for the next report. Reports received with\nunexpected index values will be rejected by the service.\n\nIn order to preserve idempotency, the worker should not alter the\ncontents of a report, even if the worker must submit the same\nreport multiple times before getting back a response. The worker\nshould not submit a subsequent report until the response for the\nprevious report had been received from the service.",
"type": "string"
},
"stopPosition": {
"$ref": "Position",
"description": "A worker may split an active map task in two parts, \"primary\" and\n\"residual\", continuing to process the primary part and returning the\nresidual part into the pool of available work.\nThis event is called a \"dynamic split\" and is critical to the dynamic\nwork rebalancing feature. The two obtained sub-tasks are called\n\"parts\" of the split.\nThe parts, if concatenated, must represent the same input as would\nbe read by the current task if the split did not happen.\nThe exact way in which the original task is decomposed into the two\nparts is specified either as a position demarcating them\n(stop_position), or explicitly as two DerivedSources, if this\ntask consumes a user-defined source type (dynamic_source_split).\n\nThe \"current\" task is adjusted as a result of the split: after a task\nwith range [A, B) sends a stop_position update at C, its range is\nconsidered to be [A, C), e.g.:\n* Progress should be interpreted relative to the new range, e.g.\n \"75% completed\" means \"75% of [A, C) completed\"\n* The worker should interpret proposed_stop_position relative to the\n new range, e.g. \"split at 68%\" should be interpreted as\n \"split at 68% of [A, C)\".\n* If the worker chooses to split again using stop_position, only\n stop_positions in [A, C) will be accepted.\n* Etc.\ndynamic_source_split has similar semantics: e.g., if a task with\nsource S splits using dynamic_source_split into {P, R}\n(where P and R must be together equivalent to S), then subsequent\nprogress and proposed_stop_position should be interpreted relative\nto P, and in a potential subsequent dynamic_source_split into {P', R'},\nP' and R' must be together equivalent to P, etc."
},
"completed": {
"type": "boolean",
"description": "True if the WorkItem was completed (successfully or unsuccessfully)."
},
"reportedProgress": {
"$ref": "ApproximateReportedProgress",
"description": "The worker's progress through this WorkItem."
},
"sourceFork": {
"$ref": "SourceFork",
"description": "DEPRECATED in favor of dynamic_source_split."
},
"totalThrottlerWaitTimeSeconds": {
"type": "number",
"format": "double",
"description": "Total time the worker spent being throttled by external systems."
},
"counterUpdates": {
"items": {
"$ref": "CounterUpdate"
},
"type": "array",
"description": "Worker output counters for this WorkItem."
}
},
"id": "WorkItemStatus"
},
"ComponentSource": {
"type": "object",
"properties": {
"originalTransformOrCollection": {
"description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
"type": "string"
},
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
},
"userName": {
"type": "string",
"description": "Human-readable name for this transform; may be user or system generated."
}
},
"id": "ComponentSource",
"description": "Description of an interstitial value between transforms in an execution\nstage."
},
"Histogram": {
"description": "Histogram of value counts for a distribution.\n\nBuckets have an inclusive lower bound and exclusive upper bound and use\n\"1,2,5 bucketing\": The first bucket range is from [0,1) and all subsequent\nbucket boundaries are powers of ten multiplied by 1, 2, or 5. Thus, bucket\nboundaries are 0, 1, 2, 5, 10, 20, 50, 100, 200, 500, 1000, ...\nNegative values are not supported.",
"type": "object",
"properties": {
"firstBucketOffset": {
"type": "integer",
"format": "int32",
"description": "Starting index of first stored bucket. The non-inclusive upper-bound of\nthe ith bucket is given by:\n pow(10,(i-first_bucket_offset)/3) * (1,2,5)[(i-first_bucket_offset)%3]"
},
"bucketCounts": {
"description": "Counts of values in each bucket. For efficiency, prefix and trailing\nbuckets with count = 0 are elided. Buckets can store the full range of\nvalues of an unsigned long, with ULLONG_MAX falling into the 59th bucket\nwith range [1e19, 2e19).",
"items": {
"type": "string",
"format": "int64"
},
"type": "array"
}
},
"id": "Histogram"
},
"WorkItemServiceState": {
"description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.",
"type": "object",
"properties": {
"suggestedStopPoint": {
"$ref": "ApproximateProgress",
"description": "DEPRECATED in favor of split_request."
},
"splitRequest": {
"$ref": "ApproximateSplitRequest",
"description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
},
"suggestedStopPosition": {
"$ref": "Position",
"description": "Obsolete, always empty."
},
"reportStatusInterval": {
"format": "google-duration",
"description": "New recommended reporting interval.",
"type": "string"
},
"harnessData": {
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "Other data returned by the service, specific to the particular\nworker harness.",
"type": "object"
},
"leaseExpireTime": {
"format": "google-datetime",
"description": "Time at which the current lease will expire.",
"type": "string"
},
"metricShortId": {
"items": {
"$ref": "MetricShortId"
},
"type": "array",
"description": "The short ids that workers should use in subsequent metric updates.\nWorkers should strive to use short ids whenever possible, but it is ok\nto request the short_id again if a worker lost track of it\n(e.g. if the worker is recovering from a crash).\nNOTE: it is possible that the response may have short ids for a subset\nof the metrics."
},
"nextReportIndex": {
"type": "string",
"format": "int64",
"description": "The index value to use for the next report sent by the worker.\nNote: If the report call fails for whatever reason, the worker should\nreuse this index for subsequent report attempts."
}
},
"id": "WorkItemServiceState"
},
"MetricStructuredName": {
"description": "Identifies a metric, by describing the source which generated the\nmetric.",
"type": "object",
"properties": {
"context": {
"additionalProperties": {
"type": "string"
},
"description": "Zero or more labeled fields which identify the part of the job this\nmetric is associated with, such as the name of a step or collection.\n\nFor example, built-in counters associated with steps will have\ncontext['step'] = \u003cstep-name\u003e. Counters associated with PCollections\nin the SDK will have context['pcollection'] = \u003cpcollection-name\u003e.",
"type": "object"
},
"name": {
"description": "Worker-defined metric name.",
"type": "string"
},
"origin": {
"description": "Origin (namespace) of metric name. May be blank for user-define metrics;\nwill be \"dataflow\" for metrics defined by the Dataflow service or SDK.",
"type": "string"
}
},
"id": "MetricStructuredName"
},
"SeqMapTaskOutputInfo": {
"description": "Information about an output of a SeqMapTask.",
"type": "object",
"properties": {
"sink": {
"$ref": "Sink",
"description": "The sink to write the output value to."
},
"tag": {
"type": "string",
"description": "The id of the TupleTag the user code will tag the output value by."
}
},
"id": "SeqMapTaskOutputInfo"
},
"JobExecutionStageInfo": {
"type": "object",
"properties": {
"stepName": {
"description": "The steps associated with the execution stage.\nNote that stages may have several steps, and that a given step\nmight be run by more than one stage.",
"items": {
"type": "string"
},
"type": "array"
}
},
"id": "JobExecutionStageInfo",
"description": "Contains information about how a particular\ngoogle.dataflow.v1beta3.Step will be executed."
},
"KeyRangeLocation": {
"description": "Location information for a specific key-range of a sharded computation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
"type": "object",
"properties": {
"deprecatedPersistentDirectory": {
"type": "string",
"description": "DEPRECATED. The location of the persistent state for this range, as a\npersistent directory in the worker local filesystem."
},
"deliveryEndpoint": {
"description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
"type": "string"
},
"dataDisk": {
"type": "string",
"description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\"."
},
"start": {
"type": "string",
"description": "The start (inclusive) of the key range."
},
"end": {
"type": "string",
"description": "The end (exclusive) of the key range."
}
},
"id": "KeyRangeLocation"
},
"SourceGetMetadataRequest": {
"description": "A request to compute the SourceMetadata of a Source.",
"type": "object",
"properties": {
"source": {
"$ref": "Source",
"description": "Specification of the source whose metadata should be computed."
}
},
"id": "SourceGetMetadataRequest"
},
"NameAndKind": {
"type": "object",
"properties": {
"name": {
"description": "Name of the counter.",
"type": "string"
},
"kind": {
"type": "string",
"enumDescriptions": [
"Counter aggregation kind was not set.",
"Aggregated value is the sum of all contributed values.",
"Aggregated value is the max of all contributed values.",
"Aggregated value is the min of all contributed values.",
"Aggregated value is the mean of all contributed values.",
"Aggregated value represents the logical 'or' of all contributed values.",
"Aggregated value represents the logical 'and' of all contributed values.",
"Aggregated value is a set of unique contributed values.",
"Aggregated value captures statistics about a distribution."
],
"enum": [
"INVALID",
"SUM",
"MAX",
"MIN",
"MEAN",
"OR",
"AND",
"SET",
"DISTRIBUTION"
],
"description": "Counter aggregation kind."
}
},
"id": "NameAndKind",
"description": "Basic metadata about a counter."
},
"SeqMapTask": {
"description": "Describes a particular function to invoke.",
"type": "object",
"properties": {
"stageName": {
"description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
"type": "string"
},
"systemName": {
"type": "string",
"description": "System-defined name of the SeqDo operation.\nUnique across the workflow."
},
"userFn": {
"type": "object",
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "The user function to invoke."
},
"name": {
"description": "The user-provided name of the SeqDo operation.",
"type": "string"
},
"outputInfos": {
"description": "Information about each of the outputs.",
"items": {
"$ref": "SeqMapTaskOutputInfo"
},
"type": "array"
},
"inputs": {
"items": {
"$ref": "SideInputInfo"
},
"type": "array",
"description": "Information about each of the inputs."
}
},
"id": "SeqMapTask"
},
"WorkerMessageCode": {
"type": "object",
"properties": {
"parameters": {
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "Parameters contains specific information about the code.\n\nThis is a struct to allow parameters of different types.\n\nExamples:\n 1. For a \"HARNESS_STARTED\" message parameters might provide the name\n of the worker and additional data like timing information.\n 2. For a \"GCS_DOWNLOAD_ERROR\" parameters might contain fields listing\n the GCS objects being downloaded and fields containing errors.\n\nIn general complex data structures should be avoided. If a worker\nneeds to send a specific and complicated data structure then please\nconsider defining a new proto and adding it to the data oneof in\nWorkerMessageResponse.\n\nConventions:\n Parameters should only be used for information that isn't typically passed\n as a label.\n hostname and other worker identifiers should almost always be passed\n as labels since they will be included on most messages.",
"type": "object"
},
"code": {
"type": "string",
"description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change."
}
},
"id": "WorkerMessageCode",
"description": "A message code is used to report status and error messages to the service.\nThe message codes are intended to be machine readable. The service will\ntake care of translating these into user understandable messages if\nnecessary.\n\nExample use cases:\n 1. Worker processes reporting successful startup.\n 2. Worker processes reporting specific errors (e.g. package staging\n failure)."
},
"CustomSourceLocation": {
"description": "Identifies the location of a custom souce.",
"type": "object",
"properties": {
"stateful": {
"type": "boolean",
"description": "Whether this source is stateful."
}
},
"id": "CustomSourceLocation"
},
"MapTask": {
"description": "MapTask consists of an ordered set of instructions, each of which\ndescribes one particular low-level operation for the worker to\nperform in order to accomplish the MapTask's WorkItem.\n\nEach instruction must appear in the list before any instructions which\ndepends on its output.",
"type": "object",
"properties": {
"stageName": {
"type": "string",
"description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow."
},
"systemName": {
"description": "System-defined name of this MapTask.\nUnique across the workflow.",
"type": "string"
},
"instructions": {
"items": {
"$ref": "ParallelInstruction"
},
"type": "array",
"description": "The instructions in the MapTask."
}
},
"id": "MapTask"
},
"FloatingPointMean": {
"type": "object",
"properties": {
"sum": {
"format": "double",
"description": "The sum of all values being aggregated.",
"type": "number"
},
"count": {
"$ref": "SplitInt64",
"description": "The number of values being aggregated."
}
},
"id": "FloatingPointMean",
"description": "A representation of a floating point mean metric contribution."
},
"ReportWorkItemStatusResponse": {
"type": "object",
"properties": {
"workItemServiceStates": {
"description": "A set of messages indicating the service-side state for each\nWorkItem whose status was reported, in the same order as the\nWorkItemStatus messages in the ReportWorkItemStatusRequest which\nresulting in this response.",
"items": {
"$ref": "WorkItemServiceState"
},
"type": "array"
}
},
"id": "ReportWorkItemStatusResponse",
"description": "Response from a request to report the status of WorkItems."
},
"InstructionOutput": {
"type": "object",
"properties": {
"originalName": {
"type": "string",
"description": "System-defined name for this output in the original workflow graph.\nOutputs that do not contribute to an original instruction do not set this."
},
"systemName": {
"type": "string",
"description": "System-defined name of this output.\nUnique across the workflow."
},
"onlyCountKeyBytes": {
"description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
"type": "boolean"
},
"onlyCountValueBytes": {
"description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
"type": "boolean"
},
"codec": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The codec to use to encode data being written via this output.",
"type": "object"
},
"name": {
"description": "The user-provided name of this output.",
"type": "string"
}
},
"id": "InstructionOutput",
"description": "An output of an instruction."
},
"CreateJobFromTemplateRequest": {
"description": "A request to create a Cloud Dataflow job from a template.",
"type": "object",
"properties": {
"jobName": {
"description": "Required. The job name to use for the created job.",
"type": "string"
},
"gcsPath": {
"description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"type": "string"
},
"environment": {
"$ref": "RuntimeEnvironment",
"description": "The runtime environment for the job."
},
"location": {
"type": "string",
"description": "The location to which to direct the request."
},
"parameters": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "The runtime parameters to pass to the job."
}
},
"id": "CreateJobFromTemplateRequest"
},
"IntegerMean": {
"type": "object",
"properties": {
"count": {
"$ref": "SplitInt64",
"description": "The number of values being aggregated."
},
"sum": {
"$ref": "SplitInt64",
"description": "The sum of all values being aggregated."
}
},
"id": "IntegerMean",
"description": "A representation of an integer mean metric contribution."
},
"ListJobsResponse": {
"description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
"type": "object",
"properties": {
"jobs": {
"items": {
"$ref": "Job"
},
"type": "array",
"description": "A subset of the requested job information."
},
"failedLocation": {
"description": "Zero or more messages describing locations that failed to respond.",
"items": {
"$ref": "FailedLocation"
},
"type": "array"
},
"nextPageToken": {
"description": "Set if there may be more results than fit in this response.",
"type": "string"
}
},
"id": "ListJobsResponse"
},
"ComputationTopology": {
"description": "All configuration data for a particular Computation.",
"type": "object",
"properties": {
"outputs": {
"items": {
"$ref": "StreamLocation"
},
"type": "array",
"description": "The outputs from the computation."
},
"stateFamilies": {
"description": "The state family values.",
"items": {
"$ref": "StateFamilyConfig"
},
"type": "array"
},
"systemStageName": {
"description": "The system stage name.",
"type": "string"
},
"computationId": {
"type": "string",
"description": "The ID of the computation."
},
"inputs": {
"items": {
"$ref": "StreamLocation"
},
"type": "array",
"description": "The inputs to the computation."
},
"keyRanges": {
"description": "The key ranges processed by the computation.",
"items": {
"$ref": "KeyRangeLocation"
},
"type": "array"
}
},
"id": "ComputationTopology"
},
"RuntimeEnvironment": {
"description": "The environment values to set at runtime.",
"type": "object",
"properties": {
"machineType": {
"description": "The machine type to use for the job. Defaults to the value from the\ntemplate if not specified.",
"type": "string"
},
"zone": {
"description": "The Compute Engine [availability\nzone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
"type": "string"
},
"maxWorkers": {
"type": "integer",
"format": "int32",
"description": "The maximum number of Google Compute Engine instances to be made\navailable to your pipeline during execution, from 1 to 1000."
},
"bypassTempDirValidation": {
"type": "boolean",
"description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution."
},
"serviceAccountEmail": {
"type": "string",
"description": "The email address of the service account to run the job as."
},
"tempLocation": {
"type": "string",
"description": "The Cloud Storage path to use for temporary files.\nMust be a valid Cloud Storage URL, beginning with `gs://`."
}
},
"id": "RuntimeEnvironment"
},
"MountedDataDisk": {
"type": "object",
"properties": {
"dataDisk": {
"type": "string",
"description": "The name of the data disk.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\"."
}
},
"id": "MountedDataDisk",
"description": "Describes mounted data disk."
},
"StreamingSideInputLocation": {
"type": "object",
"properties": {
"stateFamily": {
"description": "Identifies the state family where this side input is stored.",
"type": "string"
},
"tag": {
"description": "Identifies the particular side input within the streaming Dataflow job.",
"type": "string"
}
},
"id": "StreamingSideInputLocation",
"description": "Identifies the location of a streaming side input."
},
"LaunchTemplateResponse": {
"description": "Response to the request to launch a template.",
"type": "object",
"properties": {
"job": {
"$ref": "Job",
"description": "The job that was launched, if the request was not a dry run and\nthe job was successfully launched."
}
},
"id": "LaunchTemplateResponse"
},
"Job": {
"description": "Defines a job to be run by the Cloud Dataflow service.",
"type": "object",
"properties": {
"tempFiles": {
"items": {
"type": "string"
},
"type": "array",
"description": "A set of files the system should be aware of that are used\nfor temporary storage. These temporary files will be\nremoved on job completion.\nNo duplicates are allowed.\nNo file patterns are supported.\n\nThe supported files are:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}"
},
"clientRequestId": {
"type": "string",
"description": "The client's unique identifier of the job, re-used across retried attempts.\nIf this field is set, the service will ensure its uniqueness.\nThe request to create a job will fail if the service has knowledge of a\npreviously submitted job with the same client's ID and job name.\nThe caller may use this field to ensure idempotence of job\ncreation across retried attempts to create a job.\nBy default, the field is empty and, in that case, the service ignores it."
},
"name": {
"description": "The user-specified Cloud Dataflow job name.\n\nOnly one Job with a given name may exist in a project at any\ngiven time. If a caller attempts to create a Job with the same\nname as an already-existing Job, the attempt returns the\nexisting Job.\n\nThe name must match the regular expression\n`[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
"type": "string"
},
"steps": {
"items": {
"$ref": "Step"
},
"type": "array",
"description": "The top-level steps that constitute the entire job."
},
"replacedByJobId": {
"description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
"type": "string"
},
"id": {
"description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.",
"type": "string"
},
"executionInfo": {
"$ref": "JobExecutionInfo",
"description": "Deprecated."
},
"currentState": {
"type": "string",
"enumDescriptions": [
"The job's run state isn't specified.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
],
"enum": [
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING"
],
"description": "The current state of the job.\n\nJobs are created in the `JOB_STATE_STOPPED` state unless otherwise\nspecified.\n\nA job in the `JOB_STATE_RUNNING` state may asynchronously enter a\nterminal state. After a job has reached a terminal state, no\nfurther state updates may be made.\n\nThis field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it."
},
"location": {
"description": "The location that contains this job.",
"type": "string"
},
"currentStateTime": {
"format": "google-datetime",
"description": "The timestamp associated with the current state.",
"type": "string"
},
"transformNameMapping": {
"additionalProperties": {
"type": "string"
},
"description": "The map of transform name prefixes of the job to be replaced to the\ncorresponding name prefixes of the new job.",
"type": "object"
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "User-defined labels for this job.\n\nThe labels map can contain no more than 64 entries. Entries of the labels\nmap are UTF8 strings that comply with the following restrictions:\n\n* Keys must conform to regexp: \\p{Ll}\\p{Lo}{0,62}\n* Values must conform to regexp: [\\p{Ll}\\p{Lo}\\p{N}_-]{0,63}\n* Both keys and values are additionally constrained to be \u003c= 128 bytes in\nsize."
},
"environment": {
"$ref": "Environment",
"description": "The environment for the job."
},
"createTime": {
"type": "string",
"format": "google-datetime",
"description": "The timestamp when the job was initially created. Immutable and set by the\nCloud Dataflow service."
},
"stageStates": {
"items": {
"$ref": "ExecutionStageState"
},
"type": "array",
"description": "This field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it."
},
"type": {
"enum": [
"JOB_TYPE_UNKNOWN",
"JOB_TYPE_BATCH",
"JOB_TYPE_STREAMING"
],
"description": "The type of Cloud Dataflow job.",
"type": "string",
"enumDescriptions": [
"The type of the job is unspecified, or unknown.",
"A batch job with a well-defined end point: data is read, data is\nprocessed, data is written, and the job is done.",
"A continuously streaming job with no end: data is read,\nprocessed, and written continuously."
]
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"type": "string"
},
"pipelineDescription": {
"$ref": "PipelineDescription",
"description": "Preliminary field: The format of this data may change at any time.\nA description of the user pipeline and stages through which it is executed.\nCreated by Cloud Dataflow service. Only retrieved with\nJOB_VIEW_DESCRIPTION or JOB_VIEW_ALL."
},
"replaceJobId": {
"type": "string",
"description": "If this job is an update of an existing job, this field is the job ID\nof the job it replaced.\n\nWhen sending a `CreateJobRequest`, you can update a job by specifying it\nhere. The job named here is stopped, and its intermediate state is\ntransferred to this job."
},
"requestedState": {
"enum": [
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING"
],
"description": "The job's requested state.\n\n`UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and\n`JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may\nalso be used to directly set a job's requested state to\n`JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the\njob if it has not already reached a terminal state.",
"type": "string",
"enumDescriptions": [
"The job's run state isn't specified.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
]
}
},
"id": "Job"
},
"DynamicSourceSplit": {
"description": "When a task splits using WorkItemStatus.dynamic_source_split, this\nmessage describes the two parts of the split relative to the\ndescription of the current task's input.",
"type": "object",
"properties": {
"primary": {
"$ref": "DerivedSource",
"description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
},
"residual": {
"$ref": "DerivedSource",
"description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
}
},
"id": "DynamicSourceSplit"
},
"DerivedSource": {
"type": "object",
"properties": {
"derivationMode": {
"type": "string",
"enumDescriptions": [
"The source derivation is unknown, or unspecified.",
"Produce a completely independent Source with no base.",
"Produce a Source based on the Source being split.",
"Produce a Source based on the base of the Source being split."
],
"enum": [
"SOURCE_DERIVATION_MODE_UNKNOWN",
"SOURCE_DERIVATION_MODE_INDEPENDENT",
"SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
"SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
],
"description": "What source to base the produced source on (if any)."
},
"source": {
"$ref": "Source",
"description": "Specification of the source."
}
},
"id": "DerivedSource",
"description": "Specification of one of the bundles produced as a result of splitting\na Source (e.g. when executing a SourceSplitRequest, or when\nsplitting an active task using WorkItemStatus.dynamic_source_split),\nrelative to the source being split."
},
"SideInputId": {
"description": "Uniquely identifies a side input.",
"type": "object",
"properties": {
"declaringStepName": {
"type": "string",
"description": "The step that receives and usually consumes this side input."
},
"inputIndex": {
"type": "integer",
"format": "int32",
"description": "The index of the side input, from the list of non_parallel_inputs."
}
},
"id": "SideInputId"
},
"SourceOperationResponse": {
"description": "The result of a SourceOperationRequest, specified in\nReportWorkItemStatusRequest.source_operation when the work item\nis completed.",
"type": "object",
"properties": {
"getMetadata": {
"$ref": "SourceGetMetadataResponse",
"description": "A response to a request to get metadata about a source."
},
"split": {
"$ref": "SourceSplitResponse",
"description": "A response to a request to split a source."
}
},
"id": "SourceOperationResponse"
},
"SendDebugCaptureResponse": {
"type": "object",
"properties": {},
"id": "SendDebugCaptureResponse",
"description": "Response to a send capture request.\nnothing"
},
"SideInputInfo": {
"type": "object",
"properties": {
"tag": {
"description": "The id of the tag the user code will access this side input by;\nthis should correspond to the tag of some MultiOutputInfo.",
"type": "string"
},
"kind": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "How to interpret the source element(s) as a side input value.",
"type": "object"
},
"sources": {
"items": {
"$ref": "Source"
},
"type": "array",
"description": "The source(s) to read element(s) from to get the value of this side input.\nIf more than one source, then the elements are taken from the\nsources, in the specified order if order matters.\nAt least one source is required."
}
},
"id": "SideInputInfo",
"description": "Information about a side input of a DoFn or an input of a SeqDoFn."
},
"CounterStructuredNameAndMetadata": {
"type": "object",
"properties": {
"name": {
"$ref": "CounterStructuredName",
"description": "Structured name of the counter."
},
"metadata": {
"$ref": "CounterMetadata",
"description": "Metadata associated with a counter"
}
},
"id": "CounterStructuredNameAndMetadata",
"description": "A single message which encapsulates structured name and metadata for a given\ncounter."
},
"ConcatPosition": {
"type": "object",
"properties": {
"position": {
"$ref": "Position",
"description": "Position within the inner source."
},
"index": {
"type": "integer",
"format": "int32",
"description": "Index of the inner source."
}
},
"id": "ConcatPosition",
"description": "A position that encapsulates an inner position and an index for the inner\nposition. A ConcatPosition can be used by a reader of a source that\nencapsulates a set of other sources."
},
"WriteInstruction": {
"type": "object",
"properties": {
"sink": {
"$ref": "Sink",
"description": "The sink to write to."
},
"input": {
"$ref": "InstructionInput",
"description": "The input."
}
},
"id": "WriteInstruction",
"description": "An instruction that writes records.\nTakes one input, produces no outputs."
},
"StreamingComputationRanges": {
"type": "object",
"properties": {
"rangeAssignments": {
"items": {
"$ref": "KeyRangeDataDiskAssignment"
},
"type": "array",
"description": "Data disk assignments for ranges from this computation."
},
"computationId": {
"type": "string",
"description": "The ID of the computation."
}
},
"id": "StreamingComputationRanges",
"description": "Describes full or partial data disk assignment information of the computation\nranges."
},
"AutoscalingSettings": {
"type": "object",
"properties": {
"algorithm": {
"enum": [
"AUTOSCALING_ALGORITHM_UNKNOWN",
"AUTOSCALING_ALGORITHM_NONE",
"AUTOSCALING_ALGORITHM_BASIC"
],
"description": "The algorithm to use for autoscaling.",
"type": "string",
"enumDescriptions": [
"The algorithm is unknown, or unspecified.",
"Disable autoscaling.",
"Increase worker count over time to reduce job execution time."
]
},
"maxNumWorkers": {
"format": "int32",
"description": "The maximum number of workers to cap scaling at.",
"type": "integer"
}
},
"id": "AutoscalingSettings",
"description": "Settings for WorkerPool autoscaling."
},
"ExecutionStageSummary": {
"type": "object",
"properties": {
"outputSource": {
"description": "Output sources for this stage.",
"items": {
"$ref": "StageSource"
},
"type": "array"
},
"name": {
"type": "string",
"description": "Dataflow service generated name for this stage."
},
"inputSource": {
"items": {
"$ref": "StageSource"
},
"type": "array",
"description": "Input sources for this stage."
},
"id": {
"type": "string",
"description": "Dataflow service generated id for this stage."
},
"componentTransform": {
"items": {
"$ref": "ComponentTransform"
},
"type": "array",
"description": "Transforms that comprise this execution stage."
},
"componentSource": {
"items": {
"$ref": "ComponentSource"
},
"type": "array",
"description": "Collections produced and consumed by component transforms of this stage."
},
"kind": {
"enum": [
"UNKNOWN_KIND",
"PAR_DO_KIND",
"GROUP_BY_KEY_KIND",
"FLATTEN_KIND",
"READ_KIND",
"WRITE_KIND",
"CONSTANT_KIND",
"SINGLETON_KIND",
"SHUFFLE_KIND"
],
"description": "Type of tranform this stage is executing.",
"type": "string",
"enumDescriptions": [
"Unrecognized transform type.",
"ParDo transform.",
"Group By Key transform.",
"Flatten transform.",
"Read transform.",
"Write transform.",
"Constructs from a constant value, such as with Create.of.",
"Creates a Singleton view of a collection.",
"Opening or closing a shuffle session, often as part of a GroupByKey."
]
}
},
"id": "ExecutionStageSummary",
"description": "Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning."
},
"SendWorkerMessagesRequest": {
"type": "object",
"properties": {
"location": {
"description": "The location which contains the job",
"type": "string"
},
"workerMessages": {
"description": "The WorkerMessages to send.",
"items": {
"$ref": "WorkerMessage"
},
"type": "array"
}
},
"id": "SendWorkerMessagesRequest",
"description": "A request for sending worker messages to the service."
},
"SourceSplitShard": {
"type": "object",
"properties": {
"derivationMode": {
"type": "string",
"enumDescriptions": [
"The source derivation is unknown, or unspecified.",
"Produce a completely independent Source with no base.",
"Produce a Source based on the Source being split.",
"Produce a Source based on the base of the Source being split."
],
"enum": [
"SOURCE_DERIVATION_MODE_UNKNOWN",
"SOURCE_DERIVATION_MODE_INDEPENDENT",
"SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
"SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
],
"description": "DEPRECATED"
},
"source": {
"$ref": "Source",
"description": "DEPRECATED"
}
},
"id": "SourceSplitShard",
"description": "DEPRECATED in favor of DerivedSource."
},
"CPUTime": {
"description": "Modeled after information exposed by /proc/stat.",
"type": "object",
"properties": {
"rate": {
"format": "double",
"description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
"type": "number"
},
"timestamp": {
"format": "google-datetime",
"description": "Timestamp of the measurement.",
"type": "string"
},
"totalMs": {
"format": "uint64",
"description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
"type": "string"
}
},
"id": "CPUTime"
},
"Environment": {
"description": "Describes the environment in which a Dataflow Job runs.",
"type": "object",
"properties": {
"clusterManagerApiService": {
"type": "string",
"description": "The type of cluster manager API to use. If unknown or\nunspecified, the service will attempt to choose a reasonable\ndefault. This should be in the form of the API service name,\ne.g. \"compute.googleapis.com\"."
},
"tempStoragePrefix": {
"description": "The prefix of the resources the system should use for temporary\nstorage. The system will append the suffix \"/temp-{JOBNAME} to\nthis resource prefix, where {JOBNAME} is the value of the\njob_name field. The resulting bucket and object prefix is used\nas the prefix of the resources used to store temporary data\nneeded during the job execution. NOTE: This will override the\nvalue in taskrunner_settings.\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type": "string"
},
"workerPools": {
"description": "The worker pools. At least one \"harness\" worker pool must be\nspecified in order for the job to have workers.",
"items": {
"$ref": "WorkerPool"
},
"type": "array"
},
"dataset": {
"description": "The dataset for the current project where various workflow\nrelated tables are stored.\n\nThe supported resource type is:\n\nGoogle BigQuery:\n bigquery.googleapis.com/{dataset}",
"type": "string"
},
"experiments": {
"items": {
"type": "string"
},
"type": "array",
"description": "The list of experiments to enable."
},
"internalExperiments": {
"type": "object",
"additionalProperties": {
"type": "any",
"description": "Properties of the object. Contains field @type with type URL."
},
"description": "Experimental settings."
},
"version": {
"type": "object",
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "A structure describing which components and their versions of the service\nare required in order to run the job."
},
"serviceAccountEmail": {
"type": "string",
"description": "Identity to run virtual machines as. Defaults to the default account."
},
"userAgent": {
"type": "object",
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "A description of the process that generated the request."
},
"sdkPipelineOptions": {
"type": "object",
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "The Cloud Dataflow SDK pipeline options specified by the user. These\noptions are passed through the service and are used to recreate the\nSDK pipeline options on the worker in a language agnostic and platform\nindependent way."
}
},
"id": "Environment"
},
"StreamingComputationTask": {
"type": "object",
"properties": {
"computationRanges": {
"items": {
"$ref": "StreamingComputationRanges"
},
"type": "array",
"description": "Contains ranges of a streaming computation this task should apply to."
},
"dataDisks": {
"items": {
"$ref": "MountedDataDisk"
},
"type": "array",
"description": "Describes the set of data disks this task should apply to."
},
"taskType": {
"enum": [
"STREAMING_COMPUTATION_TASK_UNKNOWN",
"STREAMING_COMPUTATION_TASK_STOP",
"STREAMING_COMPUTATION_TASK_START"
],
"description": "A type of streaming computation task.",
"type": "string",
"enumDescriptions": [
"The streaming computation task is unknown, or unspecified.",
"Stop processing specified streaming computation range(s).",
"Start processing specified streaming computation range(s)."
]
}
},
"id": "StreamingComputationTask",
"description": "A task which describes what action should be performed for the specified\nstreaming computation ranges."
},
"SendDebugCaptureRequest": {
"description": "Request to send encoded debug information.",
"type": "object",
"properties": {
"componentId": {
"description": "The internal component id for which debug information is sent.",
"type": "string"
},
"workerId": {
"type": "string",
"description": "The worker id, i.e., VM hostname."
},
"location": {
"type": "string",
"description": "The location which contains the job specified by job_id."
},
"data": {
"description": "The encoded debug information.",
"type": "string"
}
},
"id": "SendDebugCaptureRequest"
},
"GetDebugConfigResponse": {
"type": "object",
"properties": {
"config": {
"description": "The encoded debug configuration for the requested component.",
"type": "string"
}
},
"id": "GetDebugConfigResponse",
"description": "Response to a get debug configuration request."
},
"ComponentTransform": {
"type": "object",
"properties": {
"originalTransform": {
"type": "string",
"description": "User name for the original user transform with which this transform is\nmost closely associated."
},
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
},
"userName": {
"description": "Human-readable name for this transform; may be user or system generated.",
"type": "string"
}
},
"id": "ComponentTransform",
"description": "Description of a transform executed as part of an execution stage."
},
"StreamingSetupTask": {
"description": "A task which initializes part of a streaming Dataflow job.",
"type": "object",
"properties": {
"receiveWorkPort": {
"type": "integer",
"format": "int32",
"description": "The TCP port on which the worker should listen for messages from\nother streaming computation workers."
},
"streamingComputationTopology": {
"$ref": "TopologyConfig",
"description": "The global topology of the streaming Dataflow job."
},
"drain": {
"type": "boolean",
"description": "The user has requested drain."
},
"workerHarnessPort": {
"format": "int32",
"description": "The TCP port used by the worker to communicate with the Dataflow\nworker harness.",
"type": "integer"
}
},
"id": "StreamingSetupTask"
},
"PubsubLocation": {
"type": "object",
"properties": {
"withAttributes": {
"description": "If true, then the client has requested to get pubsub attributes.",
"type": "boolean"
},
"idLabel": {
"type": "string",
"description": "If set, contains a pubsub label from which to extract record ids.\nIf left empty, record deduplication will be strictly best effort."
},
"timestampLabel": {
"type": "string",
"description": "If set, contains a pubsub label from which to extract record timestamps.\nIf left empty, record timestamps will be generated upon arrival."
},
"topic": {
"type": "string",
"description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/\u003cproject-id\u003e/\u003ctopic-name\u003e\""
},
"subscription": {
"type": "string",
"description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/\u003cproject-id\u003e/\u003csubscription-name\u003e\""
},
"dropLateData": {
"type": "boolean",
"description": "Indicates whether the pipeline allows late-arriving data."
},
"trackingSubscription": {
"description": "If set, specifies the pubsub subscription that will be used for tracking\ncustom time timestamps for watermark estimation.",
"type": "string"
}
},
"id": "PubsubLocation",
"description": "Identifies a pubsub location to use for transferring data into or\nout of a streaming Dataflow job."
},
"WorkerHealthReport": {
"description": "WorkerHealthReport contains information about the health of a worker.\n\nThe VM should be identified by the labels attached to the WorkerMessage that\nthis health ping belongs to.",
"type": "object",
"properties": {
"pods": {
"items": {
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"type": "object"
},
"type": "array",
"description": "The pods running on the worker. See:\nhttp://kubernetes.io/v1.1/docs/api-reference/v1/definitions.html#_v1_pod\n\nThis field is used by the worker to send the status of the indvidual\ncontainers running on each worker."
},
"vmStartupTime": {
"type": "string",
"format": "google-datetime",
"description": "The time the VM was booted."
},
"reportInterval": {
"format": "google-duration",
"description": "The interval at which the worker is sending health reports.\nThe default value of 0 should be interpreted as the field is not being\nexplicitly set by the worker.",
"type": "string"
},
"vmIsHealthy": {
"description": "Whether the VM is healthy.",
"type": "boolean"
}
},
"id": "WorkerHealthReport"
},
"JobMessage": {
"type": "object",
"properties": {
"messageImportance": {
"enum": [
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"description": "Importance level of the message.",
"type": "string",
"enumDescriptions": [
"The message importance isn't specified, or is unknown.",
"The message is at the 'debug' level: typically only useful for\nsoftware engineers working on the code the job is running.\nTypically, Dataflow pipeline runners do not display log messages\nat this level by default.",
"The message is at the 'detailed' level: somewhat verbose, but\npotentially useful to users. Typically, Dataflow pipeline\nrunners do not display log messages at this level by default.\nThese messages are displayed by default in the Dataflow\nmonitoring UI.",
"The message is at the 'basic' level: useful for keeping\ntrack of the execution of a Dataflow pipeline. Typically,\nDataflow pipeline runners display log messages at this level by\ndefault, and these messages are displayed by default in the\nDataflow monitoring UI.",
"The message is at the 'warning' level: indicating a condition\npertaining to a job which may require human intervention.\nTypically, Dataflow pipeline runners display log messages at this\nlevel by default, and these messages are displayed by default in\nthe Dataflow monitoring UI.",
"The message is at the 'error' level: indicating a condition\npreventing a job from succeeding. Typically, Dataflow pipeline\nrunners display log messages at this level by default, and these\nmessages are displayed by default in the Dataflow monitoring UI."
]
},
"messageText": {
"type": "string",
"description": "The text of the message."
},
"time": {
"type": "string",
"format": "google-datetime",
"description": "The timestamp of the message."
},
"id": {
"description": "Deprecated.",
"type": "string"
}
},
"id": "JobMessage",
"description": "A particular message pertaining to a Dataflow job."
},
"ParameterMetadata": {
"description": "Metadata for a specific parameter.",
"type": "object",
"properties": {
"helpText": {
"description": "Required. The help text to display for the parameter.",
"type": "string"
},
"isOptional": {
"type": "boolean",
"description": "Optional. Whether the parameter is optional. Defaults to false."
},
"name": {
"type": "string",
"description": "Required. The name of the parameter."
},
"regexes": {
"items": {
"type": "string"
},
"type": "array",
"description": "Optional. Regexes that the parameter must match."
},
"label": {
"description": "Required. The label to display for the parameter.",
"type": "string"
}
},
"id": "ParameterMetadata"
},
"MultiOutputInfo": {
"type": "object",
"properties": {
"tag": {
"description": "The id of the tag the user code will emit to this output by; this\nshould correspond to the tag of some SideInputInfo.",
"type": "string"
}
},
"id": "MultiOutputInfo",
"description": "Information about an output of a multi-output DoFn."
},
"SourceSplitRequest": {
"description": "Represents the operation to split a high-level Source specification\ninto bundles (parts for parallel processing).\n\nAt a high level, splitting of a source into bundles happens as follows:\nSourceSplitRequest is applied to the source. If it returns\nSOURCE_SPLIT_OUTCOME_USE_CURRENT, no further splitting happens and the source\nis used \"as is\". Otherwise, splitting is applied recursively to each\nproduced DerivedSource.\n\nAs an optimization, for any Source, if its does_not_need_splitting is\ntrue, the framework assumes that splitting this source would return\nSOURCE_SPLIT_OUTCOME_USE_CURRENT, and doesn't initiate a SourceSplitRequest.\nThis applies both to the initial source being split and to bundles\nproduced from it.",
"type": "object",
"properties": {
"options": {
"$ref": "SourceSplitOptions",
"description": "Hints for tuning the splitting process."
},
"source": {
"$ref": "Source",
"description": "Specification of the source to be split."
}
},
"id": "SourceSplitRequest"
},
"SourceGetMetadataResponse": {
"type": "object",
"properties": {
"metadata": {
"$ref": "SourceMetadata",
"description": "The computed metadata."
}
},
"id": "SourceGetMetadataResponse",
"description": "The result of a SourceGetMetadataOperation."
},
"AutoscalingEvent": {
"type": "object",
"properties": {
"currentNumWorkers": {
"type": "string",
"format": "int64",
"description": "The current number of workers the job has."
},
"time": {
"type": "string",
"format": "google-datetime",
"description": "The time this event was emitted to indicate a new target or current\nnum_workers value."
},
"description": {
"$ref": "StructuredMessage",
"description": "A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
},
"eventType": {
"type": "string",
"enumDescriptions": [
"Default type for the enum. Value should never be returned.",
"The TARGET_NUM_WORKERS_CHANGED type should be used when the target\nworker pool size has changed at the start of an actuation. An event\nshould always be specified as TARGET_NUM_WORKERS_CHANGED if it reflects\na change in the target_num_workers.",
"The CURRENT_NUM_WORKERS_CHANGED type should be used when actual worker\npool size has been changed, but the target_num_workers has not changed.",
"The ACTUATION_FAILURE type should be used when we want to report\nan error to the user indicating why the current number of workers\nin the pool could not be changed.\nDisplayed in the current status and history widgets.",
"Used when we want to report to the user a reason why we are\nnot currently adjusting the number of workers.\nShould specify both target_num_workers, current_num_workers and a\ndecision_message."
],
"enum": [
"TYPE_UNKNOWN",
"TARGET_NUM_WORKERS_CHANGED",
"CURRENT_NUM_WORKERS_CHANGED",
"ACTUATION_FAILURE",
"NO_CHANGE"
],
"description": "The type of autoscaling event to report."
},
"targetNumWorkers": {
"format": "int64",
"description": "The target number of workers the worker pool wants to resize to use.",
"type": "string"
}
},
"id": "AutoscalingEvent",
"description": "A structured message reporting an autoscaling decision made by the Dataflow\nservice."
},
"MetricShortId": {
"description": "The metric short id is returned to the user alongside an offset into\nReportWorkItemStatusRequest",
"type": "object",
"properties": {
"shortId": {
"type": "string",
"format": "int64",
"description": "The service-generated short identifier for the metric."
},
"metricIndex": {
"type": "integer",
"format": "int32",
"description": "The index of the corresponding metric in\nthe ReportWorkItemStatusRequest. Required."
}
},
"id": "MetricShortId"
},
"ShellTask": {
"description": "A task which consists of a shell command for the worker to execute.",
"type": "object",
"properties": {
"exitCode": {
"type": "integer",
"format": "int32",
"description": "Exit code for the task."
},
"command": {
"description": "The shell command to run.",
"type": "string"
}
},
"id": "ShellTask"
},
"TaskRunnerSettings": {
"description": "Taskrunner configuration settings.",
"type": "object",
"properties": {
"workflowFileName": {
"description": "The file to store the workflow in.",
"type": "string"
},
"languageHint": {
"type": "string",
"description": "The suggested backend language."
},
"commandlinesFileName": {
"type": "string",
"description": "The file to store preprocessing commands in."
},
"tempStoragePrefix": {
"type": "string",
"description": "The prefix of the resources the taskrunner should use for\ntemporary storage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}"
},
"baseTaskDir": {
"description": "The location on the worker for task-specific subdirectories.",
"type": "string"
},
"baseUrl": {
"description": "The base URL for the taskrunner to use when accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
"type": "string"
},
"logToSerialconsole": {
"type": "boolean",
"description": "Whether to send taskrunner log info to Google Compute Engine VM serial\nconsole."
},
"continueOnException": {
"type": "boolean",
"description": "Whether to continue taskrunner if an exception is hit."
},
"parallelWorkerSettings": {
"$ref": "WorkerSettings",
"description": "The settings to pass to the parallel worker harness."
},
"vmId": {
"description": "The ID string of the VM.",
"type": "string"
},
"taskUser": {
"type": "string",
"description": "The UNIX user ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"root\"."
},
"alsologtostderr": {
"type": "boolean",
"description": "Whether to also send taskrunner log info to stderr."
},
"taskGroup": {
"description": "The UNIX group ID on the worker VM to use for tasks launched by\ntaskrunner; e.g. \"wheel\".",
"type": "string"
},
"harnessCommand": {
"type": "string",
"description": "The command to launch the worker harness."
},
"logDir": {
"type": "string",
"description": "The directory on the VM to store logs."
},
"dataflowApiVersion": {
"description": "The API version of endpoint, e.g. \"v1b3\"",
"type": "string"
},
"oauthScopes": {
"items": {
"type": "string"
},
"type": "array",
"description": "The OAuth2 scopes to be requested by the taskrunner in order to\naccess the Cloud Dataflow API."
},
"logUploadLocation": {
"type": "string",
"description": "Indicates where to put logs. If this is not specified, the logs\nwill not be uploaded.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}"
},
"streamingWorkerMainClass": {
"description": "The streaming worker main class name.",
"type": "string"
}
},
"id": "TaskRunnerSettings"
},
"Position": {
"description": "Position defines a position within a collection of data. The value\ncan be either the end position, a key (used with ordered\ncollections), a byte offset, or a record index.",
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "Position is a string key, ordered lexicographically."
},
"recordIndex": {
"type": "string",
"format": "int64",
"description": "Position is a record index."
},
"shufflePosition": {
"description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED\nsharding).",
"type": "string"
},
"concatPosition": {
"$ref": "ConcatPosition",
"description": "CloudPosition is a concat position."
},
"byteOffset": {
"type": "string",
"format": "int64",
"description": "Position is a byte offset."
},
"end": {
"type": "boolean",
"description": "Position is past all other positions. Also useful for the end\nposition of an unbounded range."
}
},
"id": "Position"
},
"Source": {
"type": "object",
"properties": {
"metadata": {
"$ref": "SourceMetadata",
"description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
},
"baseSpecs": {
"items": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"type": "object"
},
"type": "array",
"description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs)."
},
"doesNotNeedSplitting": {
"type": "boolean",
"description": "Setting this value to true hints to the framework that the source\ndoesn't need splitting, and using SourceSplitRequest on it would\nyield SOURCE_SPLIT_OUTCOME_USE_CURRENT.\n\nE.g. a file splitter may set this to true when splitting a single file\ninto a set of byte ranges of appropriate size, and set this\nto false when splitting a filepattern into individual files.\nHowever, for efficiency, a file splitter may decide to produce\nfile subranges directly from the filepattern to avoid a splitting\nround-trip.\n\nSee SourceSplitRequest for an overview of the splitting process.\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
},
"codec": {
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "The codec to use to decode data read from the source.",
"type": "object"
},
"spec": {
"type": "object",
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "The source to read from, plus its parameters."
}
},
"id": "Source",
"description": "A source that records can be read and decoded from."
},
"SplitInt64": {
"type": "object",
"properties": {
"highBits": {
"format": "int32",
"description": "The high order bits, including the sign: n \u003e\u003e 32.",
"type": "integer"
},
"lowBits": {
"type": "integer",
"format": "uint32",
"description": "The low order bits: n & 0xffffffff."
}
},
"id": "SplitInt64",
"description": "A representation of an int64, n, that is immune to precision loss when\nencoded in JSON."
},
"WorkerPool": {
"description": "Describes one particular pool of Cloud Dataflow workers to be\ninstantiated by the Cloud Dataflow service in order to perform the\ncomputations required by a job. Note that a workflow job may use\nmultiple pools, in order to match the various computational\nrequirements of the various stages of the job.",
"type": "object",
"properties": {
"subnetwork": {
"description": "Subnetwork to which VMs will be assigned, if desired. Expected to be of\nthe form \"regions/REGION/subnetworks/SUBNETWORK\".",
"type": "string"
},
"ipConfiguration": {
"enum": [
"WORKER_IP_UNSPECIFIED",
"WORKER_IP_PUBLIC",
"WORKER_IP_PRIVATE"
],
"description": "Configuration for VM IPs.",
"type": "string",
"enumDescriptions": [
"The configuration is unknown, or unspecified.",
"Workers should have public IP addresses.",
"Workers should have private IP addresses."
]
},
"autoscalingSettings": {
"$ref": "AutoscalingSettings",
"description": "Settings for autoscaling of this WorkerPool."
},
"taskrunnerSettings": {
"$ref": "TaskRunnerSettings",
"description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
},
"metadata": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Metadata to set on the Google Compute Engine VMs."
},
"defaultPackageSet": {
"type": "string",
"enumDescriptions": [
"The default set of packages to stage is unknown, or unspecified.",
"Indicates that no packages should be staged at the worker unless\nexplicitly specified by the job.",
"Stage packages typically useful to workers written in Java.",
"Stage pacakges typically useful to workers written in Python."
],
"enum": [
"DEFAULT_PACKAGE_SET_UNKNOWN",
"DEFAULT_PACKAGE_SET_NONE",
"DEFAULT_PACKAGE_SET_JAVA",
"DEFAULT_PACKAGE_SET_PYTHON"
],
"description": "The default package set to install. This allows the service to\nselect a default set of packages which are useful to worker\nharnesses written in a particular language."
},
"network": {
"description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
"type": "string"
},
"zone": {
"description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
"type": "string"
},
"numWorkers": {
"format": "int32",
"description": "Number of Google Compute Engine workers in this pool needed to\nexecute the job. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
"type": "integer"
},
"numThreadsPerWorker": {
"type": "integer",
"format": "int32",
"description": "The number of threads per worker harness. If empty or unspecified, the\nservice will choose a number of threads (according to the number of cores\non the selected machine type for batch, or 1 by convention for streaming)."
},
"diskSourceImage": {
"description": "Fully qualified source image for disks.",
"type": "string"
},
"packages": {
"items": {
"$ref": "Package"
},
"type": "array",
"description": "Packages to be installed on workers."
},
"teardownPolicy": {
"enum": [
"TEARDOWN_POLICY_UNKNOWN",
"TEARDOWN_ALWAYS",
"TEARDOWN_ON_SUCCESS",
"TEARDOWN_NEVER"
],
"description": "Sets the policy for determining when to turndown worker pool.\nAllowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and\n`TEARDOWN_NEVER`.\n`TEARDOWN_ALWAYS` means workers are always torn down regardless of whether\nthe job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down\nif the job succeeds. `TEARDOWN_NEVER` means the workers are never torn\ndown.\n\nIf the workers are not torn down by the service, they will\ncontinue to run and use Google Compute Engine VM resources in the\nuser's project until they are explicitly terminated by the user.\nBecause of this, Google recommends using the `TEARDOWN_ALWAYS`\npolicy except for small, manually supervised test jobs.\n\nIf unknown or unspecified, the service will attempt to choose a reasonable\ndefault.",
"type": "string",
"enumDescriptions": [
"The teardown policy isn't specified, or is unknown.",
"Always teardown the resource.",
"Teardown the resource on success. This is useful for debugging\nfailures.",
"Never teardown the resource. This is useful for debugging and\ndevelopment."
]
},
"onHostMaintenance": {
"description": "The action to take on host maintenance, as defined by the Google\nCompute Engine API.",
"type": "string"
},
"poolArgs": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "Extra arguments for this worker pool.",
"type": "object"
},
"diskSizeGb": {
"type": "integer",
"format": "int32",
"description": "Size of root disk for VMs, in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default."
},
"workerHarnessContainerImage": {
"description": "Required. Docker container image that executes the Cloud Dataflow worker\nharness, residing in Google Container Registry.",
"type": "string"
},
"machineType": {
"description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
"type": "string"
},
"diskType": {
"description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
"type": "string"
},
"kind": {
"type": "string",
"description": "The kind of the worker pool; currently only `harness` and `shuffle`\nare supported."
},
"dataDisks": {
"items": {
"$ref": "Disk"
},
"type": "array",
"description": "Data disks that are used by a VM in this workflow."
}
},
"id": "WorkerPool"
},
"SourceOperationRequest": {
"type": "object",
"properties": {
"getMetadata": {
"$ref": "SourceGetMetadataRequest",
"description": "Information about a request to get metadata about a source."
},
"split": {
"$ref": "SourceSplitRequest",
"description": "Information about a request to split a source."
}
},
"id": "SourceOperationRequest",
"description": "A work item that represents the different operations that can be\nperformed on a user-defined Source specification."
},
"WorkItem": {
"description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.",
"type": "object",
"properties": {
"initialReportIndex": {
"type": "string",
"format": "int64",
"description": "The initial index to use when reporting the status of the WorkItem."
},
"shellTask": {
"$ref": "ShellTask",
"description": "Additional information for ShellTask WorkItems."
},
"streamingComputationTask": {
"$ref": "StreamingComputationTask",
"description": "Additional information for StreamingComputationTask WorkItems."
},
"jobId": {
"type": "string",
"description": "Identifies the workflow job this WorkItem belongs to."
},
"id": {
"format": "int64",
"description": "Identifies this WorkItem.",
"type": "string"
},
"configuration": {
"description": "Work item-specific configuration as an opaque blob.",
"type": "string"
},
"mapTask": {
"$ref": "MapTask",
"description": "Additional information for MapTask WorkItems."
},
"seqMapTask": {
"$ref": "SeqMapTask",
"description": "Additional information for SeqMapTask WorkItems."
},
"packages": {
"description": "Any required packages that need to be fetched in order to execute\nthis WorkItem.",
"items": {
"$ref": "Package"
},
"type": "array"
},
"projectId": {
"description": "Identifies the cloud project this WorkItem belongs to.",
"type": "string"
},
"reportStatusInterval": {
"type": "string",
"format": "google-duration",
"description": "Recommended reporting interval."
},
"streamingSetupTask": {
"$ref": "StreamingSetupTask",
"description": "Additional information for StreamingSetupTask WorkItems."
},
"sourceOperationTask": {
"$ref": "SourceOperationRequest",
"description": "Additional information for source operation WorkItems."
},
"leaseExpireTime": {
"type": "string",
"format": "google-datetime",
"description": "Time when the lease on this Work will expire."
},
"streamingConfigTask": {
"$ref": "StreamingConfigTask",
"description": "Additional information for StreamingConfigTask WorkItems."
}
},
"id": "WorkItem"
},
"StructuredMessage": {
"type": "object",
"properties": {
"messageKey": {
"description": "Idenfier for this message type. Used by external systems to\ninternationalize or personalize message.",
"type": "string"
},
"messageText": {
"description": "Human-readable version of message.",
"type": "string"
},
"parameters": {
"description": "The structured data associated with this message.",
"items": {
"$ref": "Parameter"
},
"type": "array"
}
},
"id": "StructuredMessage",
"description": "A rich message format, including a human readable string, a key for\nidentifying the message, and structured data associated with the message for\nprogrammatic consumption."
},
"ReportedParallelism": {
"type": "object",
"properties": {
"isInfinite": {
"type": "boolean",
"description": "Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack."
},
"value": {
"type": "number",
"format": "double",
"description": "Specifies the level of parallelism in case it is finite."
}
},
"id": "ReportedParallelism",
"description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker."
},
"ResourceUtilizationReport": {
"description": "Worker metrics exported from workers. This contains resource utilization\nmetrics accumulated from a variety of sources. For more information, see\ngo/df-resource-signals.",
"type": "object",
"properties": {
"cpuTime": {
"description": "CPU utilization samples.",
"items": {
"$ref": "CPUTime"
},
"type": "array"
}
},
"id": "ResourceUtilizationReport"
},
"TopologyConfig": {
"description": "Global topology of the streaming Dataflow job, including all\ncomputations and their sharded locations.",
"type": "object",
"properties": {
"forwardingKeyBits": {
"type": "integer",
"format": "int32",
"description": "The size (in bits) of keys that will be assigned to source messages."
},
"userStageToComputationNameMap": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Maps user stage names to stable computation names."
},
"computations": {
"description": "The computations associated with a streaming Dataflow job.",
"items": {
"$ref": "ComputationTopology"
},
"type": "array"
},
"persistentStateVersion": {
"format": "int32",
"description": "Version number for persistent state.",
"type": "integer"
},
"dataDiskAssignments": {
"description": "The disks assigned to a streaming Dataflow job.",
"items": {
"$ref": "DataDiskAssignment"
},
"type": "array"
}
},
"id": "TopologyConfig"
},
"SourceSplitOptions": {
"description": "Hints for splitting a Source into bundles (parts for parallel\nprocessing) using SourceSplitRequest.",
"type": "object",
"properties": {
"desiredBundleSizeBytes": {
"format": "int64",
"description": "The source should be split into a set of bundles where the estimated size\nof each is approximately this many bytes.",
"type": "string"
},
"desiredShardSizeBytes": {
"format": "int64",
"description": "DEPRECATED in favor of desired_bundle_size_bytes.",
"type": "string"
}
},
"id": "SourceSplitOptions"
},
"ReadInstruction": {
"type": "object",
"properties": {
"source": {
"$ref": "Source",
"description": "The source to read from."
}
},
"id": "ReadInstruction",
"description": "An instruction that reads records.\nTakes no inputs, produces one output."
},
"WorkerSettings": {
"type": "object",
"properties": {
"reportingEnabled": {
"description": "Whether to send work progress updates to the service.",
"type": "boolean"
},
"baseUrl": {
"type": "string",
"description": "The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\""
},
"servicePath": {
"type": "string",
"description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\"."
},
"shuffleServicePath": {
"description": "The Shuffle service path relative to the root URL, for example,\n\"shuffle/v1beta1\".",
"type": "string"
},
"workerId": {
"description": "The ID of the worker running this pipeline.",
"type": "string"
},
"tempStoragePrefix": {
"description": "The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type": "string"
}
},
"id": "WorkerSettings",
"description": "Provides data to pass through to the worker harness."
},
"StreamingStageLocation": {
"type": "object",
"properties": {
"streamId": {
"description": "Identifies the particular stream within the streaming Dataflow\njob.",
"type": "string"
}
},
"id": "StreamingStageLocation",
"description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication."
},
"DataDiskAssignment": {
"description": "Data disk assignment for a given VM instance.",
"type": "object",
"properties": {
"vmInstance": {
"type": "string",
"description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\"."
},
"dataDisks": {
"description": "Mounted data disks. The order is important a data disk's 0-based index in\nthis list defines which persistent directory the disk is mounted to, for\nexample the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" },\n{ \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
"items": {
"type": "string"
},
"type": "array"
}
},
"id": "DataDiskAssignment"
},
"ApproximateSplitRequest": {
"type": "object",
"properties": {
"position": {
"$ref": "Position",
"description": "A Position at which to split the work item."
},
"fractionConsumed": {
"format": "double",
"description": "A fraction at which to split the work item, from 0.0 (beginning of the\ninput) to 1.0 (end of the input).",
"type": "number"
}
},
"id": "ApproximateSplitRequest",
"description": "A suggestion by the service to the worker to dynamically split the WorkItem."
},
"Status": {
"type": "object",
"properties": {
"code": {
"type": "integer",
"format": "int32",
"description": "The status code, which should be an enum value of google.rpc.Code."
},
"message": {
"type": "string",
"description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client."
},
"details": {
"items": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"type": "object"
},
"type": "array",
"description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use."
}
},
"id": "Status",
"description": "The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` that can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons."
},
"ExecutionStageState": {
"description": "A message describing the state of a particular execution stage.",
"type": "object",
"properties": {
"currentStateTime": {
"type": "string",
"format": "google-datetime",
"description": "The time at which the stage transitioned to this state."
},
"executionStageState": {
"type": "string",
"enumDescriptions": [
"The job's run state isn't specified.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"'JOB_STATE_PENDING' indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"'JOB_STATE_CANCELLING' indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to 'JOB_STATE_CANCELLED' or 'JOB_STATE_FAILED'."
],
"enum": [
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING"
],
"description": "Executions stage states allow the same set of values as JobState."
},
"executionStageName": {
"description": "The name of the execution stage.",
"type": "string"
}
},
"id": "ExecutionStageState"
},
"StreamLocation": {
"description": "Describes a stream of data, either as input to be processed or as\noutput of a streaming Dataflow job.",
"type": "object",
"properties": {
"customSourceLocation": {
"$ref": "CustomSourceLocation",
"description": "The stream is a custom source."
},
"sideInputLocation": {
"$ref": "StreamingSideInputLocation",
"description": "The stream is a streaming side input."
},
"pubsubLocation": {
"$ref": "PubsubLocation",
"description": "The stream is a pubsub stream."
},
"streamingStageLocation": {
"$ref": "StreamingStageLocation",
"description": "The stream is part of another computation within the current\nstreaming Dataflow job."
}
},
"id": "StreamLocation"
},
"SendWorkerMessagesResponse": {
"type": "object",
"properties": {
"workerMessageResponses": {
"items": {
"$ref": "WorkerMessageResponse"
},
"type": "array",
"description": "The servers response to the worker messages."
}
},
"id": "SendWorkerMessagesResponse",
"description": "The response to the worker messages."
},
"StreamingComputationConfig": {
"description": "Configuration information for a single streaming computation.",
"type": "object",
"properties": {
"computationId": {
"description": "Unique identifier for this computation.",
"type": "string"
},
"stageName": {
"description": "Stage name of this computation.",
"type": "string"
},
"systemName": {
"type": "string",
"description": "System defined name for this computation."
},
"instructions": {
"description": "Instructions that comprise the computation.",
"items": {
"$ref": "ParallelInstruction"
},
"type": "array"
}
},
"id": "StreamingComputationConfig"
},
"TransformSummary": {
"type": "object",
"properties": {
"inputCollectionName": {
"description": "User names for all collection inputs to this transform.",
"items": {
"type": "string"
},
"type": "array"
},
"name": {
"type": "string",
"description": "User provided name for this transform instance."
},
"id": {
"description": "SDK generated id of this transform instance.",
"type": "string"
},
"displayData": {
"description": "Transform-specific display data.",
"items": {
"$ref": "DisplayData"
},
"type": "array"
},
"outputCollectionName": {
"description": "User names for all collection outputs to this transform.",
"items": {
"type": "string"
},
"type": "array"
},
"kind": {
"type": "string",
"enumDescriptions": [
"Unrecognized transform type.",
"ParDo transform.",
"Group By Key transform.",
"Flatten transform.",
"Read transform.",
"Write transform.",
"Constructs from a constant value, such as with Create.of.",
"Creates a Singleton view of a collection.",
"Opening or closing a shuffle session, often as part of a GroupByKey."
],
"enum": [
"UNKNOWN_KIND",
"PAR_DO_KIND",
"GROUP_BY_KEY_KIND",
"FLATTEN_KIND",
"READ_KIND",
"WRITE_KIND",
"CONSTANT_KIND",
"SINGLETON_KIND",
"SHUFFLE_KIND"
],
"description": "Type of transform."
}
},
"id": "TransformSummary",
"description": "Description of the type, names/ids, and input/outputs for a transform."
},
"LeaseWorkItemResponse": {
"description": "Response to a request to lease WorkItems.",
"type": "object",
"properties": {
"workItems": {
"description": "A list of the leased WorkItems.",
"items": {
"$ref": "WorkItem"
},
"type": "array"
}
},
"id": "LeaseWorkItemResponse"
},
"LaunchTemplateParameters": {
"description": "Parameters to provide to the template being launched.",
"type": "object",
"properties": {
"jobName": {
"type": "string",
"description": "Required. The job name to use for the created job."
},
"environment": {
"$ref": "RuntimeEnvironment",
"description": "The runtime environment for the job."
},
"parameters": {
"additionalProperties": {
"type": "string"
},
"description": "The runtime parameters to pass to the job.",
"type": "object"
}
},
"id": "LaunchTemplateParameters"
},
"Sink": {
"description": "A sink that records can be encoded and written to.",
"type": "object",
"properties": {
"codec": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The codec to use to encode data written to the sink.",
"type": "object"
},
"spec": {
"type": "object",
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The sink to write to, plus its parameters."
}
},
"id": "Sink"
},
"FlattenInstruction": {
"description": "An instruction that copies its inputs (zero or more) to its (single) output.",
"type": "object",
"properties": {
"inputs": {
"description": "Describes the inputs to the flatten instruction.",
"items": {
"$ref": "InstructionInput"
},
"type": "array"
}
},
"id": "FlattenInstruction"
},
"PartialGroupByKeyInstruction": {
"description": "An instruction that does a partial group-by-key.\nOne input and one output.",
"type": "object",
"properties": {
"input": {
"$ref": "InstructionInput",
"description": "Describes the input to the partial group-by-key instruction."
},
"inputElementCodec": {
"type": "object",
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The codec to use for interpreting an element in the input PTable."
},
"valueCombiningFn": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The value combining function to invoke.",
"type": "object"
},
"originalCombineValuesInputStoreName": {
"type": "string",
"description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues."
},
"sideInputs": {
"description": "Zero or more side inputs.",
"items": {
"$ref": "SideInputInfo"
},
"type": "array"
},
"originalCombineValuesStepName": {
"type": "string",
"description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction."
}
},
"id": "PartialGroupByKeyInstruction"
},
"StageSource": {
"type": "object",
"properties": {
"sizeBytes": {
"type": "string",
"format": "int64",
"description": "Size of the source, if measurable."
},
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
},
"userName": {
"description": "Human-readable name for this source; may be user or system generated.",
"type": "string"
},
"originalTransformOrCollection": {
"type": "string",
"description": "User name for the original user transform or collection with which this\nsource is most closely associated."
}
},
"id": "StageSource",
"description": "Description of an input or output of an execution stage."
},
"InstructionInput": {
"type": "object",
"properties": {
"producerInstructionIndex": {
"format": "int32",
"description": "The index (origin zero) of the parallel instruction that produces\nthe output to be consumed by this input. This index is relative\nto the list of instructions in this input's instruction's\ncontaining MapTask.",
"type": "integer"
},
"outputNum": {
"format": "int32",
"description": "The output index (origin zero) within the producer.",
"type": "integer"
}
},
"id": "InstructionInput",
"description": "An input of an instruction, as a reference to an output of a\nproducer instruction."
},
"StringList": {
"description": "A metric value representing a list of strings.",
"type": "object",
"properties": {
"elements": {
"items": {
"type": "string"
},
"type": "array",
"description": "Elements of the list."
}
},
"id": "StringList"
},
"DisplayData": {
"description": "Data provided with a pipeline or transform to provide descriptive info.",
"type": "object",
"properties": {
"label": {
"description": "An optional label to display in a dax UI for the element.",
"type": "string"
},
"url": {
"description": "An optional full URL.",
"type": "string"
},
"timestampValue": {
"format": "google-datetime",
"description": "Contains value if the data is of timestamp type.",
"type": "string"
},
"javaClassValue": {
"description": "Contains value if the data is of java class type.",
"type": "string"
},
"boolValue": {
"description": "Contains value if the data is of a boolean type.",
"type": "boolean"
},
"strValue": {
"description": "Contains value if the data is of string type.",
"type": "string"
},
"int64Value": {
"type": "string",
"format": "int64",
"description": "Contains value if the data is of int64 type."
},
"durationValue": {
"type": "string",
"format": "google-duration",
"description": "Contains value if the data is of duration type."
},
"namespace": {
"type": "string",
"description": "The namespace for the key. This is usually a class name or programming\nlanguage namespace (i.e. python module) which defines the display data.\nThis allows a dax monitoring system to specially handle the data\nand perform custom rendering."
},
"floatValue": {
"type": "number",
"format": "float",
"description": "Contains value if the data is of float type."
},
"key": {
"description": "The key identifying the display data.\nThis is intended to be used as a label for the display data\nwhen viewed in a dax monitoring system.",
"type": "string"
},
"shortStrValue": {
"description": "A possible additional shorter value to display.\nFor example a java_class_name_value of com.mypackage.MyDoFn\nwill be stored with MyDoFn as the short_str_value and\ncom.mypackage.MyDoFn as the java_class_name value.\nshort_str_value can be displayed and java_class_name_value\nwill be displayed as a tooltip.",
"type": "string"
}
},
"id": "DisplayData"
},
"LeaseWorkItemRequest": {
"description": "Request to lease WorkItems.",
"type": "object",
"properties": {
"requestedLeaseDuration": {
"type": "string",
"format": "google-duration",
"description": "The initial lease period."
},
"currentWorkerTime": {
"format": "google-datetime",
"description": "The current timestamp at the worker.",
"type": "string"
},
"workItemTypes": {
"items": {
"type": "string"
},
"type": "array",
"description": "Filter for WorkItem type."
},
"location": {
"type": "string",
"description": "The location which contains the WorkItem's job."
},
"workerCapabilities": {
"description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
"items": {
"type": "string"
},
"type": "array"
},
"workerId": {
"description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
"type": "string"
}
},
"id": "LeaseWorkItemRequest"
},
"GetDebugConfigRequest": {
"type": "object",
"properties": {
"componentId": {
"type": "string",
"description": "The internal component id for which debug configuration is\nrequested."
},
"workerId": {
"type": "string",
"description": "The worker id, i.e., VM hostname."
},
"location": {
"type": "string",
"description": "The location which contains the job specified by job_id."
}
},
"id": "GetDebugConfigRequest",
"description": "Request to get updated debug configuration for component."
},
"GetTemplateResponse": {
"type": "object",
"properties": {
"status": {
"$ref": "Status",
"description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
},
"metadata": {
"$ref": "TemplateMetadata",
"description": "The template metadata describing the template name, available\nparameters, etc."
}
},
"id": "GetTemplateResponse",
"description": "The response to a GetTemplate request."
},
"Parameter": {
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "Key or name for this parameter."
},
"value": {
"type": "any",
"description": "Value for this parameter."
}
},
"id": "Parameter",
"description": "Structured data associated with this message."
},
"ReportWorkItemStatusRequest": {
"description": "Request to report the status of WorkItems.",
"type": "object",
"properties": {
"location": {
"description": "The location which contains the WorkItem's job.",
"type": "string"
},
"workItemStatuses": {
"description": "The order is unimportant, except that the order of the\nWorkItemServiceState messages in the ReportWorkItemStatusResponse\ncorresponds to the order of WorkItemStatus messages here.",
"items": {
"$ref": "WorkItemStatus"
},
"type": "array"
},
"currentWorkerTime": {
"format": "google-datetime",
"description": "The current timestamp at the worker.",
"type": "string"
},
"workerId": {
"description": "The ID of the worker reporting the WorkItem status. If this\ndoes not match the ID of the worker which the Dataflow service\nbelieves currently has the lease on the WorkItem, the report\nwill be dropped (with an error response).",
"type": "string"
}
},
"id": "ReportWorkItemStatusRequest"
},
"PipelineDescription": {
"type": "object",
"properties": {
"displayData": {
"description": "Pipeline level display data.",
"items": {
"$ref": "DisplayData"
},
"type": "array"
},
"executionPipelineStage": {
"description": "Description of each stage of execution of the pipeline.",
"items": {
"$ref": "ExecutionStageSummary"
},
"type": "array"
},
"originalPipelineTransform": {
"items": {
"$ref": "TransformSummary"
},
"type": "array",
"description": "Description of each transform in the pipeline and collections between them."
}
},
"id": "PipelineDescription",
"description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics."
},
"StreamingConfigTask": {
"type": "object",
"properties": {
"streamingComputationConfigs": {
"description": "Set of computation configuration information.",
"items": {
"$ref": "StreamingComputationConfig"
},
"type": "array"
},
"windmillServiceEndpoint": {
"type": "string",
"description": "If present, the worker must use this endpoint to communicate with Windmill\nService dispatchers, otherwise the worker must continue to use whatever\nendpoint it had been using."
},
"userStepToStateFamilyNameMap": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Map from user step names to state families."
},
"windmillServicePort": {
"format": "int64",
"description": "If present, the worker must use this port to communicate with Windmill\nService dispatchers. Only applicable when windmill_service_endpoint is\nspecified.",
"type": "string"
}
},
"id": "StreamingConfigTask",
"description": "A task that carries configuration information for streaming computations."
},
"JobExecutionInfo": {
"description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.",
"type": "object",
"properties": {
"stages": {
"additionalProperties": {
"$ref": "JobExecutionStageInfo"
},
"description": "A mapping from each stage to the information about that stage.",
"type": "object"
}
},
"id": "JobExecutionInfo"
},
"Step": {
"description": "Defines a particular step within a Cloud Dataflow job.\n\nA job consists of multiple steps, each of which performs some\nspecific operation as part of the overall job. Data is typically\npassed from one step to another as part of the job.\n\nHere's an example of a sequence of steps which together implement a\nMap-Reduce job:\n\n * Read a collection of data from some source, parsing the\n collection's elements.\n\n * Validate the elements.\n\n * Apply a user-defined function to map each element to some value\n and extract an element-specific key value.\n\n * Group elements with the same key into a single element with\n that key, transforming a multiply-keyed collection into a\n uniquely-keyed collection.\n\n * Write the elements out to some data sink.\n\nNote that the Cloud Dataflow service may be used to run many different\ntypes of jobs, not just Map-Reduce.",
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The name that identifies the step. This must be unique for each\nstep with respect to all other steps in the Cloud Dataflow job."
},
"kind": {
"description": "The kind of step in the Cloud Dataflow job.",
"type": "string"
},
"properties": {
"additionalProperties": {
"type": "any",
"description": "Properties of the object."
},
"description": "Named properties associated with the step. Each kind of\npredefined step has its own required set of properties.\nMust be provided on Create. Only retrieved with JOB_VIEW_ALL.",
"type": "object"
}
},
"id": "Step"
},
"FailedLocation": {
"type": "object",
"properties": {
"name": {
"description": "The name of the failed location.",
"type": "string"
}
},
"id": "FailedLocation",
"description": "Indicates which location failed to respond to a request for data."
},
"Disk": {
"type": "object",
"properties": {
"diskType": {
"type": "string",
"description": "Disk storage type, as defined by Google Compute Engine. This\nmust be a disk type appropriate to the project and zone in which\nthe workers will run. If unknown or unspecified, the service\nwill attempt to choose a reasonable default.\n\nFor example, the standard persistent disk type is a resource name\ntypically ending in \"pd-standard\". If SSD persistent disks are\navailable, the resource name typically ends with \"pd-ssd\". The\nactual valid values are defined the Google Compute Engine API,\nnot by the Cloud Dataflow API; consult the Google Compute Engine\ndocumentation for more information about determining the set of\navailable disk types for a particular project and zone.\n\nGoogle Compute Engine Disk types are local to a particular\nproject in a particular zone, and so the resource name will\ntypically look something like this:\n\ncompute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard"
},
"sizeGb": {
"type": "integer",
"format": "int32",
"description": "Size of disk in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default."
},
"mountPoint": {
"description": "Directory in a VM where disk is mounted.",
"type": "string"
}
},
"id": "Disk",
"description": "Describes the data disk used by a workflow job."
},
"ListJobMessagesResponse": {
"description": "Response to a request to list job messages.",
"type": "object",
"properties": {
"autoscalingEvents": {
"description": "Autoscaling events in ascending timestamp order.",
"items": {
"$ref": "AutoscalingEvent"
},
"type": "array"
},
"jobMessages": {
"description": "Messages in ascending timestamp order.",
"items": {
"$ref": "JobMessage"
},
"type": "array"
},
"nextPageToken": {
"description": "The token to obtain the next page of results if there are more.",
"type": "string"
}
},
"id": "ListJobMessagesResponse"
},
"CounterMetadata": {
"description": "CounterMetadata includes all static non-name non-value counter attributes.",
"type": "object",
"properties": {
"standardUnits": {
"type": "string",
"enumDescriptions": [
"Counter returns a value in bytes.",
"Counter returns a value in bytes per second.",
"Counter returns a value in milliseconds.",
"Counter returns a value in microseconds.",
"Counter returns a value in nanoseconds.",
"Counter returns a timestamp in milliseconds.",
"Counter returns a timestamp in microseconds.",
"Counter returns a timestamp in nanoseconds."
],
"enum": [
"BYTES",
"BYTES_PER_SEC",
"MILLISECONDS",
"MICROSECONDS",
"NANOSECONDS",
"TIMESTAMP_MSEC",
"TIMESTAMP_USEC",
"TIMESTAMP_NSEC"
],
"description": "System defined Units, see above enum."
},
"otherUnits": {
"type": "string",
"description": "A string referring to the unit type."
},
"description": {
"type": "string",
"description": "Human-readable description of the counter semantics."
},
"kind": {
"type": "string",
"enumDescriptions": [
"Counter aggregation kind was not set.",
"Aggregated value is the sum of all contributed values.",
"Aggregated value is the max of all contributed values.",
"Aggregated value is the min of all contributed values.",
"Aggregated value is the mean of all contributed values.",
"Aggregated value represents the logical 'or' of all contributed values.",
"Aggregated value represents the logical 'and' of all contributed values.",
"Aggregated value is a set of unique contributed values.",
"Aggregated value captures statistics about a distribution."
],
"enum": [
"INVALID",
"SUM",
"MAX",
"MIN",
"MEAN",
"OR",
"AND",
"SET",
"DISTRIBUTION"
],
"description": "Counter aggregation kind."
}
},
"id": "CounterMetadata"
},
"ApproximateReportedProgress": {
"description": "A progress measurement of a WorkItem by a worker.",
"type": "object",
"properties": {
"remainingParallelism": {
"$ref": "ReportedParallelism",
"description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
},
"position": {
"$ref": "Position",
"description": "A Position within the work to represent a progress."
},
"fractionConsumed": {
"type": "number",
"format": "double",
"description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed)."
},
"consumedParallelism": {
"$ref": "ReportedParallelism",
"description": "Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
}
},
"id": "ApproximateReportedProgress"
},
"StateFamilyConfig": {
"type": "object",
"properties": {
"stateFamily": {
"type": "string",
"description": "The state family value."
},
"isRead": {
"type": "boolean",
"description": "If true, this family corresponds to a read operation."
}
},
"id": "StateFamilyConfig",
"description": "State family configuration."
},
"IntegerList": {
"type": "object",
"properties": {
"elements": {
"items": {
"$ref": "SplitInt64"
},
"type": "array",
"description": "Elements of the list."
}
},
"id": "IntegerList",
"description": "A metric value representing a list of integers."
},
"ResourceUtilizationReportResponse": {
"type": "object",
"properties": {},
"id": "ResourceUtilizationReportResponse",
"description": "Service-side response to WorkerMessage reporting resource utilization."
},
"SourceSplitResponse": {
"type": "object",
"properties": {
"bundles": {
"items": {
"$ref": "DerivedSource"
},
"type": "array",
"description": "If outcome is SPLITTING_HAPPENED, then this is a list of bundles\ninto which the source was split. Otherwise this field is ignored.\nThis list can be empty, which means the source represents an empty input."
},
"shards": {
"items": {
"$ref": "SourceSplitShard"
},
"type": "array",
"description": "DEPRECATED in favor of bundles."
},
"outcome": {
"type": "string",
"enumDescriptions": [
"The source split outcome is unknown, or unspecified.",
"The current source should be processed \"as is\" without splitting.",
"Splitting produced a list of bundles."
],
"enum": [
"SOURCE_SPLIT_OUTCOME_UNKNOWN",
"SOURCE_SPLIT_OUTCOME_USE_CURRENT",
"SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED"
],
"description": "Indicates whether splitting happened and produced a list of bundles.\nIf this is USE_CURRENT_SOURCE_AS_IS, the current source should\nbe processed \"as is\" without splitting. \"bundles\" is ignored in this case.\nIf this is SPLITTING_HAPPENED, then \"bundles\" contains a list of\nbundles into which the source was split."
}
},
"id": "SourceSplitResponse",
"description": "The response to a SourceSplitRequest."
},
"ParallelInstruction": {
"description": "Describes a particular operation comprising a MapTask.",
"type": "object",
"properties": {
"outputs": {
"items": {
"$ref": "InstructionOutput"
},
"type": "array",
"description": "Describes the outputs of the instruction."
},
"name": {
"type": "string",
"description": "User-provided name of this operation."
},
"read": {
"$ref": "ReadInstruction",
"description": "Additional information for Read instructions."
},
"parDo": {
"$ref": "ParDoInstruction",
"description": "Additional information for ParDo instructions."
},
"flatten": {
"$ref": "FlattenInstruction",
"description": "Additional information for Flatten instructions."
},
"originalName": {
"description": "System-defined name for the operation in the original workflow graph.",
"type": "string"
},
"write": {
"$ref": "WriteInstruction",
"description": "Additional information for Write instructions."
},
"systemName": {
"description": "System-defined name of this operation.\nUnique across the workflow.",
"type": "string"
},
"partialGroupByKey": {
"$ref": "PartialGroupByKeyInstruction",
"description": "Additional information for PartialGroupByKey instructions."
}
},
"id": "ParallelInstruction"
},
"KeyRangeDataDiskAssignment": {
"type": "object",
"properties": {
"dataDisk": {
"description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
"type": "string"
},
"start": {
"description": "The start (inclusive) of the key range.",
"type": "string"
},
"end": {
"type": "string",
"description": "The end (exclusive) of the key range."
}
},
"id": "KeyRangeDataDiskAssignment",
"description": "Data disk assignment information for a specific key-range of a sharded\ncomputation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON."
},
"Package": {
"type": "object",
"properties": {
"location": {
"description": "The resource to read the package from. The supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}\n bucket.storage.googleapis.com/",
"type": "string"
},
"name": {
"type": "string",
"description": "The name of the package."
}
},
"id": "Package",
"description": "The packages that must be installed in order for a worker to run the\nsteps of the Cloud Dataflow job that will be assigned to its worker\npool.\n\nThis is the mechanism by which the Cloud Dataflow SDK causes code to\nbe loaded onto the workers. For example, the Cloud Dataflow Java SDK\nmight use this to install jars containing the user's code and all of the\nvarious dependencies (libraries, data files, etc.) required in order\nfor that code to run."
}
},
"protocol": "rest",
"icons": {
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
"version": "v1b3",
"baseUrl": "https://dataflow.googleapis.com/"
}